_mm512_cvtfxpnt_round_adjustepu32_ps _mm512_cvtfxpnt_round_adjustps_epi32 _mm512_cvtfxpnt_round_adjustps_epu32 _mm512_mask_cosd_ps _mm512_mask_cvtfxpnt_round_adjustepu32_ps _mm512_mask_cvtfxpnt_round_adjustps_epi32 _mm512_mask_sind_ps _mm512_set_epi32 _mm512_set1_epi32 _mm512_set4_epi32 _mm512_setr4_epi32 Intel® MIC Architecture features    mmic    watch    offload-option    no-offload    option building an application that runs natively    option showing passed options    option specifying options to be used for a specified target and tool    option to ignore language constructs for offloading Intel® MIC class libraries, introducing options passed to offload compilation    watch    option listing all __INTEL_OFFLOAD    Writing Code that Should Not Be Built for CPU-Only Execution    Writing Target-Specific Code Using a Pragma __MIC__    Overview: Using a Pragma    Writing Target-Specific Code Using a Pragma __regcall _Cilk_offload    Rules for Using _Cilk_shared and _Cilk_offload    keyword _Cilk_offload_to    _Cilk_offload    keyword _Cilk_shared    Rules for Using _Cilk_shared and _Cilk_offload    keyword _may_i_use_cpu_feature _mm_clevict _mm_countbits _mm_delay_32 _mm_delay_64 _mm_div_epi16 _mm_div_epi32 _mm_div_epi64 _mm_div_epi8/ _mm_div_epu16 _mm_div_epu32 _mm_div_epu64 _mm_div_epu8 _mm_rem_epi16 _mm_rem_epi32 _mm_rem_epi64 _mm_rem_epi8 _mm_rem_epu16 _mm_rem_epu32 _mm_rem_epu64 _mm_rem_epu8 _mm_spflt_32 _mm_spflt_64 _mm_tzcnt_32 _mm_tzcnt_64 _mm_tzcnti_32 _mm_tzcnti_64 _mm256_div_epi16 _mm256_div_epi32 _mm256_div_epi64 _mm256_div_epi8 _mm256_div_epu16 _mm256_div_epu32 _mm256_div_epu64 _mm256_div_epu8 _mm256_rem_epi16 _mm256_rem_epi32 _mm256_rem_epi64 _mm256_rem_epi8 _mm256_rem_epu16 _mm256_rem_epu32 _mm256_rem_epu64 _mm256_rem_epu8 _mm512_acos_pd _mm512_acos_ps _mm512_acosh_pd _mm512_acosh_ps _mm512_adc_epi32 _mm512_add_epi32 _mm512_add_epi64 _mm512_add_pd _mm512_add_ps _mm512_add_round_pd _mm512_add_round_ps _mm512_addn_pd _mm512_addn_ps _mm512_addn_round_pd _mm512_addn_round_ps _mm512_addsetc_epi32 _mm512_addsets_epi32 _mm512_addsets_ps _mm512_addsets_round_ps _mm512_alignr_epi32 _mm512_and_epi32 _mm512_and_epi64 _mm512_andnot_epi32 _mm512_andnot_epi64 _mm512_asin_pd _mm512_asin_ps _mm512_asinh_pd _mm512_asinh_ps _mm512_atan_pd _mm512_atan_ps _mm512_atan2_pd _mm512_atan2_ps _mm512_atanh_pd _mm512_atanh_ps _mm512_castpd_ps _mm512_castpd_si512 _mm512_castps_pd _mm512_castps_si512 _mm512_castsi512_pd _mm512_castsi512_ps _mm512_cbrt_pd _mm512_cbrt_ps _mm512_cdfnorminv_pd _mm512_cdfnorminv_ps _mm512_ceil_pd _mm512_ceil_ps _mm512_cmp_epu32_mask _mm512_cmp_pd_mask _mm512_cmp_ps_mask _mm512_cmpeq_epi32_mask _mm512_cos_pd _mm512_cos_ps _mm512_cosd_pd _mm512_cosd_ps _mm512_cosh_pd _mm512_cosh_ps _mm512_cvt_roundpd_epi32lo _mm512_cvt_roundpd_pslo _mm512_cvtepi32lo_pd _mm512_cvtepu32lo_pd _mm512_cvtfxpnt_round_adjustepu32_ps _mm512_cvtfxpnt_roundpd_epu32lo _mm512_cvtpd_pslo _mm512_cvtpslo_pd _mm512_div_epi16 _mm512_div_epi32 _mm512_div_epi64 _mm512_div_epi8 _mm512_div_epu16 _mm512_div_epu32 _mm512_div_epu64 _mm512_div_epu8 _mm512_div_pd _mm512_div_ps _mm512_erf_pd _mm512_erf_ps _mm512_erfc_pd _mm512_erfc_ps _mm512_erfinv_pd _mm512_erfinv_ps _mm512_exp_pd _mm512_exp_ps _mm512_exp10_pd _mm512_exp10_ps _mm512_exp2_pd _mm512_exp2_ps _mm512_exp223_ps _mm512_expm1_pd _mm512_expm1_ps _mm512_extload_epi32 _mm512_extload_epi64 _mm512_extload_pd _mm512_extload_ps _mm512_extloadunpackhi_epi32 _mm512_extloadunpackhi_epi64 _mm512_extloadunpackhi_pd _mm512_extloadunpackhi_ps _mm512_extloadunpacklo_epi32 _mm512_extloadunpacklo_epi64 _mm512_extloadunpacklo_pd _mm512_extloadunpacklo_ps _mm512_extpackstorehi_epi32 _mm512_extpackstorehi_epi64 _mm512_extpackstorehi_pd _mm512_extpackstorehi_ps _mm512_extpackstorelo_epi32 _mm512_extpackstorelo_epi64 _mm512_extpackstorelo_pd _mm512_extpackstorelo_ps _mm512_extstore_epi32 _mm512_extstore_epi64 _mm512_extstore_pd _mm512_extstore_ps _mm512_fixupnan_pd _mm512_fixupnan_ps _mm512_floor_pd _mm512_floor_ps _mm512_fmadd_epi32 _mm512_fmadd_pd _mm512_fmadd_ps _mm512_fmadd_round_pd _mm512_fmadd_round_ps _mm512_fmadd233_epi32 _mm512_fmadd233_ps _mm512_fmadd233_round_ps _mm512_fmsub_pd _mm512_fmsub_ps _mm512_fmsub_round_pd _mm512_fmsub_round_ps _mm512_fnmadd_pd _mm512_fnmadd_ps _mm512_fnmadd_round_pd _mm512_fnmadd_round_ps _mm512_fnmsub_pd _mm512_fnmsub_ps _mm512_fnmsub_round_pd _mm512_fnmsub_round_ps _mm512_getexp_pd _mm512_getexp_ps _mm512_getmant_pd _mm512_getmant_ps _mm512_gmax_ps _mm512_gmaxabs_ps _mm512_gmin_pd _mm512_gmin_ps _mm512_hypot_pd _mm512_hypot_ps _mm512_i32extgather_epi32 _mm512_i32extgather_ps _mm512_i32extscatter_ps _mm512_i32gather_epi32 _mm512_i32gather_ps _mm512_i32loextgather_epi64 _mm512_i32loextgather_pd _mm512_i32loextscatter_epi64 _mm512_i32loextscatter_pd _mm512_i32logather_epi64 _mm512_i32logather_pd _mm512_i32loscatter_epi64 _mm512_i32loscatter_pd _mm512_i32scatter_ps    _mm512_i32[ext]gather_ps/ _mm512_mask_i32[ext]gather_ps    _mm512_i32[ext]scatter_ps/ _mm512_mask_i32[ext]scatter_ps _mm512_int2mask _mm512_invsqrt_pd _mm512_invsqrt_ps _mm512_kand _mm512_kandn _mm512_kandnr _mm512_kconcathi_64 _mm512_kconcatlo_64 _mm512_kextract_64 _mm512_kmov _mm512_knot _mm512_kor _mm512_kortestc _mm512_kortestz _mm512_kswapb _mm512_kxnor _mm512_kxor _mm512_load_epi32 _mm512_load_epi64 _mm512_load_pd _mm512_load_ps _mm512_loadunpackhi_epi32 _mm512_loadunpackhi_epi64 _mm512_loadunpackhi_pd _mm512_loadunpackhi_ps _mm512_loadunpacklo_epi32 _mm512_loadunpacklo_epi64 _mm512_loadunpacklo_pd _mm512_loadunpacklo_ps _mm512_log_pd _mm512_log_ps _mm512_log10_pd _mm512_log10_ps _mm512_log1p_pd _mm512_log1p_ps _mm512_log2_pd _mm512_log2_ps _mm512_log2ae23_ps _mm512_logb_pd _mm512_logb_ps _mm512_mask_acos_pd _mm512_mask_acos_ps _mm512_mask_acosh_pd _mm512_mask_acosh_ps _mm512_mask_adc_epi32 _mm512_mask_add_epi32 _mm512_mask_add_epi64 _mm512_mask_add_pd _mm512_mask_add_ps _mm512_mask_add_round_pd _mm512_mask_add_round_ps _mm512_mask_addn_pd _mm512_mask_addn_ps _mm512_mask_addn_round_pd _mm512_mask_addn_round_ps _mm512_mask_addsetc_epi32 _mm512_mask_addsets_epi32 _mm512_mask_addsets_ps _mm512_mask_addsets_round_ps _mm512_mask_alignr_epi32 _mm512_mask_and_epi32 _mm512_mask_and_epi64 _mm512_mask_andnot_epi32 _mm512_mask_andnot_epi64 _mm512_mask_asin_pd _mm512_mask_asin_ps _mm512_mask_asinh_pd _mm512_mask_asinh_ps _mm512_mask_atan_pd _mm512_mask_atan_ps _mm512_mask_atan2_pd _mm512_mask_atan2_ps _mm512_mask_atanh_pd _mm512_mask_atanh_ps _mm512_mask_cbrt_pd _mm512_mask_cbrt_ps _mm512_mask_cdfnorminv_pd _mm512_mask_cdfnorminv_ps _mm512_mask_ceil_pd _mm512_mask_ceil_ps _mm512_mask_cmp_epi32_mask _mm512_mask_cmp_epu32_mask _mm512_mask_cmp_pd_mask _mm512_mask_cmp_ps_mask _mm512_mask_cos_pd _mm512_mask_cos_ps _mm512_mask_cosd_pd _mm512_mask_cosh_pd _mm512_mask_cosh_ps _mm512_mask_cvt_roundpd_epi32lo _mm512_mask_cvt_roundpd_pslo _mm512_mask_cvtepi32lo_pd _mm512_mask_cvtepu32lo_pd _mm512_mask_cvtfxpnt_round_adjustepu32_ps _mm512_mask_cvtfxpnt_round_adjustps_epu32 _mm512_mask_cvtfxpnt_roundpd_epu32lo _mm512_mask_cvtpd_pslo _mm512_mask_cvtpslo_pd _mm512_mask_div_epi32 _mm512_mask_div_epu32 _mm512_mask_div_pd _mm512_mask_div_ps _mm512_mask_erf_pd _mm512_mask_erf_ps _mm512_mask_erfc_pd _mm512_mask_erfc_ps _mm512_mask_erfinv_pd _mm512_mask_erfinv_ps _mm512_mask_exp_pd _mm512_mask_exp_ps _mm512_mask_exp10_pd _mm512_mask_exp10_ps _mm512_mask_exp2_pd _mm512_mask_exp2_ps _mm512_mask_exp223_ps _mm512_mask_expm1_pd _mm512_mask_expm1_ps _mm512_mask_extload_epi32 _mm512_mask_extload_epi64 _mm512_mask_extload_pd _mm512_mask_extload_ps _mm512_mask_extloadunpackhi_epi32 _mm512_mask_extloadunpackhi_epi64 _mm512_mask_extloadunpackhi_pd _mm512_mask_extloadunpackhi_ps _mm512_mask_extloadunpacklo_epi32 _mm512_mask_extloadunpacklo_epi64 _mm512_mask_extloadunpacklo_pd _mm512_mask_extloadunpacklo_ps _mm512_mask_extpackstorehi_epi32 _mm512_mask_extpackstorehi_epi64 _mm512_mask_extpackstorehi_pd _mm512_mask_extpackstorehi_ps _mm512_mask_extpackstorelo_epi32 _mm512_mask_extpackstorelo_epi64 _mm512_mask_extpackstorelo_pd _mm512_mask_extpackstorelo_ps _mm512_mask_extstore_epi32 _mm512_mask_extstore_epi64 _mm512_mask_extstore_pd _mm512_mask_extstore_ps _mm512_mask_fixupnan_pd _mm512_mask_fixupnan_ps _mm512_mask_floor_pd _mm512_mask_floor_ps _mm512_mask_fmadd_epi32 _mm512_mask_fmadd_pd _mm512_mask_fmadd_ps _mm512_mask_fmadd_round_pd _mm512_mask_fmadd_round_ps _mm512_mask_fmadd233_epi32 _mm512_mask_fmadd233_ps _mm512_mask_fmadd233_round_ps _mm512_mask_fmsub_pd _mm512_mask_fmsub_ps _mm512_mask_fmsub_round_pd _mm512_mask_fmsub_round_ps _mm512_mask_fnmadd_pd _mm512_mask_fnmadd_ps _mm512_mask_fnmadd_round_pd _mm512_mask_fnmadd_round_ps _mm512_mask_fnmsub_pd _mm512_mask_fnmsub_ps _mm512_mask_fnmsub_round_pd _mm512_mask_fnmsub_round_ps _mm512_mask_getexp_pd _mm512_mask_getexp_ps _mm512_mask_getmant_pd _mm512_mask_getmant_ps _mm512_mask_gmax_ps _mm512_mask_gmaxabs_ps _mm512_mask_gmin_pd _mm512_mask_gmin_ps _mm512_mask_hypot_pd _mm512_mask_hypot_ps _mm512_mask_i32extgather_epi32 _mm512_mask_i32extgather_ps _mm512_mask_i32extscatter_ps _mm512_mask_i32gather_epi32 _mm512_mask_i32gather_ps _mm512_mask_i32loextgather_epi64 _mm512_mask_i32loextgather_pd _mm512_mask_i32loextscatter_epi64 _mm512_mask_i32loextscatter_pd _mm512_mask_i32logather_epi64 _mm512_mask_i32logather_pd _mm512_mask_i32loscatter_epi64 _mm512_mask_i32loscatter_pd _mm512_mask_i32scatter_ps    _mm512_i32[ext]gather_ps/ _mm512_mask_i32[ext]gather_ps    _mm512_i32[ext]scatter_ps/ _mm512_mask_i32[ext]scatter_ps _mm512_mask_invsqrt_pd _mm512_mask_invsqrt_ps _mm512_mask_load_epi32 _mm512_mask_load_epi64 _mm512_mask_load_pd _mm512_mask_load_ps _mm512_mask_loadunpackhi_epi32 _mm512_mask_loadunpackhi_epi64 _mm512_mask_loadunpackhi_pd _mm512_mask_loadunpackhi_ps _mm512_mask_loadunpacklo_epi32 _mm512_mask_loadunpacklo_epi64 _mm512_mask_loadunpacklo_pd _mm512_mask_loadunpacklo_ps _mm512_mask_log_ps _mm512_mask_log10_pd _mm512_mask_log10_ps _mm512_mask_log1p_pd _mm512_mask_log1p_ps _mm512_mask_log2_pd _mm512_mask_log2_ps _mm512_mask_log2ae23_ps _mm512_mask_logb_pd _mm512_mask_logb_ps _mm512_mask_max_epi32 _mm512_mask_max_epu32 _mm512_mask_max_pd    _mm512_max_pd/ _mm512_mask_max_pd    _mm512_gmax_pd/ _mm512_mask_gmax_pd _mm512_mask_max_ps _mm512_mask_maxabs_ps _mm512_mask_mov_epi32 _mm512_mask_mov_epi64 _mm512_mask_mov_pd _mm512_mask_mov_ps _mm512_mask_mul_pd _mm512_mask_mul_ps _mm512_mask_mul_round_pd _mm512_mask_mul_round_ps _mm512_mask_mulhi_epi32 _mm512_mask_mulhi_epu32 _mm512_mask_mullo_epi32 _mm512_mask_nearbyint_ps    _mm512_nearbyint_pd/ _mm512_mask_nearbyint_pd    _mm512_nearbyint_ps/ _mm512_mask_nearbyint_ps _mm512_mask_or_epi32 _mm512_mask_or_epi64 _mm512_mask_packstorehi_epi32 _mm512_mask_packstorehi_epi64 _mm512_mask_packstorehi_pd _mm512_mask_packstorehi_ps _mm512_mask_packstorelo_epi32 _mm512_mask_packstorelo_epi64 _mm512_mask_packstorelo_pd _mm512_mask_packstorelo_ps _mm512_mask_permute4f128_epi32 _mm512_mask_permutevar_epi32 _mm512_mask_pow_pd _mm512_mask_pow_ps _mm512_mask_prefetch_i32extgather_ps _mm512_mask_prefetch_i32extscatter_ps _mm512_mask_prefetch_i32gather_ps _mm512_mask_prefetch_i32scatter_ps _mm512_mask_rcp23_ps _mm512_mask_reduce_add_epi32 _mm512_mask_reduce_add_pd _mm512_mask_reduce_add_ps _mm512_mask_reduce_and_epi32 _mm512_mask_reduce_gmax_pd _mm512_mask_reduce_gmax_ps _mm512_mask_reduce_gmin_pd _mm512_mask_reduce_gmin_ps _mm512_mask_reduce_max_epi32 _mm512_mask_reduce_max_epu32 _mm512_mask_reduce_max_pd _mm512_mask_reduce_max_ps _mm512_mask_reduce_min_epi32 _mm512_mask_reduce_min_epu32 _mm512_mask_reduce_min_pd _mm512_mask_reduce_min_ps _mm512_mask_reduce_mul_epi32 _mm512_mask_reduce_mul_pd _mm512_mask_reduce_mul_ps _mm512_mask_reduce_or_epi32 _mm512_mask_rem_epi32 _mm512_mask_rem_epu32 _mm512_mask_rint_pd _mm512_mask_rint_ps _mm512_mask_round_ps _mm512_mask_roundfxpnt_adjust_pd _mm512_mask_roundfxpnt_adjust_ps _mm512_mask_rsqrt23_ps _mm512_mask_sbb_epi32 _mm512_mask_sbbr_epi32 _mm512_mask_scale_ps _mm512_mask_scale_round_ps _mm512_mask_shuffle_epi32 _mm512_mask_sin_pd _mm512_mask_sin_ps _mm512_mask_sind_pd _mm512_mask_sinh_pd _mm512_mask_sinh_ps _mm512_mask_slli_epi32 _mm512_mask_sllv_epi32 _mm512_mask_sqrt_pd _mm512_mask_sqrt_ps _mm512_mask_srai_epi32 _mm512_mask_srav_epi32 _mm512_mask_srli_epi32 _mm512_mask_srlv_epi32 _mm512_mask_store_epi32 _mm512_mask_store_epi64 _mm512_mask_store_pd _mm512_mask_store_ps _mm512_mask_sub_epi32 _mm512_mask_sub_pd _mm512_mask_sub_ps _mm512_mask_sub_round_pd _mm512_mask_sub_round_ps _mm512_mask_subr_epi32 _mm512_mask_subr_pd _mm512_mask_subr_ps _mm512_mask_subr_round_pd _mm512_mask_subr_round_ps _mm512_mask_subrsetb_epi32 _mm512_mask_subsetb_epi32 _mm512_mask_svml_round_pd _mm512_mask_swizzle_epi32 _mm512_mask_swizzle_epi64 _mm512_mask_swizzle_pd _mm512_mask_swizzle_ps _mm512_mask_tan_pd _mm512_mask_tan_ps _mm512_mask_tand_pd _mm512_mask_tand_ps _mm512_mask_tanh_pd _mm512_mask_tanh_ps _mm512_mask_test_epi32_mask _mm512_mask_trunc_pd _mm512_mask_trunc_ps _mm512_mask_xor_epi32 _mm512_mask_xor_epi64 _mm512_mask2int _mm512_mask3_fmadd_epi32 _mm512_mask3_fmadd_pd _mm512_mask3_fmadd_ps _mm512_mask3_fmadd_round_pd _mm512_mask3_fmadd_round_ps _mm512_mask3_fmsub_pd _mm512_mask3_fmsub_ps _mm512_mask3_fmsub_round_pd _mm512_mask3_fmsub_round_ps _mm512_mask3_fnmadd_pd _mm512_mask3_fnmadd_ps _mm512_mask3_fnmadd_round_pd _mm512_mask3_fnmadd_round_ps _mm512_mask3_fnmsub_pd _mm512_mask3_fnmsub_ps _mm512_mask3_fnmsub_round_pd _mm512_mask3_fnmsub_round_ps _mm512_masklog_pd _mm512_max_epi32 _mm512_max_epu32 _mm512_max_pd    _mm512_max_pd/ _mm512_mask_max_pd    _mm512_gmax_pd/ _mm512_mask_gmax_pd _mm512_max_ps _mm512_maxabs_ps _mm512_min_epi32 _mm512_min_epu32 _mm512_min_pd _mm512_min_ps _mm512_movlhb _mm512_mul_pd _mm512_mul_ps _mm512_mul_round_pd _mm512_mul_round_ps _mm512_mulhi_epi32 _mm512_mulhi_epu32 _mm512_mullo_epi32 _mm512_nearbyint_pd _mm512_nearbyint_ps _mm512_or_epi32 _mm512_or_epi64 _mm512_packstorehi_epi32 _mm512_packstorehi_epi64 _mm512_packstorehi_pd _mm512_packstorehi_ps _mm512_packstorelo_epi32 _mm512_packstorelo_epi64 _mm512_packstorelo_pd _mm512_packstorelo_ps _mm512_permute4f128_epi32 _mm512_permutevar_epi32 _mm512_pow_pd _mm512_pow_ps _mm512_prefetch_i32extgather_ps _mm512_prefetch_i32extscatter_ps _mm512_prefetch_i32gather_ps _mm512_prefetch_i32scatter_ps _mm512_rcp23_ps _mm512_reduce_add_epi32 _mm512_reduce_add_pd _mm512_reduce_add_ps _mm512_reduce_and_epi32 _mm512_reduce_gmax_pd _mm512_reduce_gmax_ps _mm512_reduce_gmin_pd _mm512_reduce_gmin_ps _mm512_reduce_max_epi32 _mm512_reduce_max_epu32 _mm512_reduce_max_pd _mm512_reduce_max_ps _mm512_reduce_min_epi32 _mm512_reduce_min_epu32 _mm512_reduce_min_pd _mm512_reduce_min_ps _mm512_reduce_mul_epi32 _mm512_reduce_mul_pd _mm512_reduce_mul_ps _mm512_reduce_or_epi32 _mm512_rem_epi16 _mm512_rem_epi32 _mm512_rem_epi64 _mm512_rem_epi8 _mm512_rem_epu16 _mm512_rem_epu32 _mm512_rem_epu64 _mm512_rem_epu8 _mm512_rint_pd _mm512_rint_ps _mm512_round_ps _mm512_roundfxpnt_adjust_pd _mm512_roundfxpnt_adjust_ps _mm512_rsqrt23_ps _mm512_sbb_epi32 _mm512_sbbr_epi32 _mm512_scale_ps _mm512_scale_round_ps _mm512_set_epi64 _mm512_set_pd _mm512_set_ps _mm512_set1_epi64 _mm512_set1_pd _mm512_set1_ps _mm512_set4_epi64 _mm512_set4_pd _mm512_set4_ps _mm512_setr_epi64 _mm512_setr_pd _mm512_setr_ps _mm512_setr4_epi64 _mm512_setr4_pd _mm512_setr4_ps _mm512_setzero_epi32 _mm512_setzero_pd _mm512_setzero_ps _mm512_shuffle_epi32 _mm512_sin_pd _mm512_sin_ps _mm512_sind_pd _mm512_sind_ps _mm512_sinh_pd _mm512_sinh_ps _mm512_slli_epi32 _mm512_sllv_epi32 _mm512_sqrt_pd _mm512_sqrt_ps _mm512_srai_epi32 _mm512_srav_epi32 _mm512_srli_epi32 _mm512_srlv_epi32 _mm512_store_epi32 _mm512_store_epi64 _mm512_store_pd _mm512_store_ps _mm512_storenr_pd _mm512_storenr_ps _mm512_storenrngo_pd _mm512_storenrngo_ps _mm512_sub_epi32 _mm512_sub_pd _mm512_sub_ps _mm512_sub_round_pd _mm512_sub_round_ps _mm512_subr_epi32 _mm512_subr_pd _mm512_subr_ps _mm512_subr_round_pd _mm512_subr_round_ps _mm512_subrsetb_epi32 _mm512_subsetb_epi32 _mm512_svml_round_pd _mm512_swizzle_epi32 _mm512_swizzle_epi64 _mm512_swizzle_pd _mm512_swizzle_ps _mm512_tan_pd _mm512_tan_ps _mm512_tand_pd _mm512_tand_ps _mm512_tanh_pd _mm512_tanh_ps _mm512_test_epi32_mask _mm512_trunc_pd _mm512_trunc_ps _mm512_undefined_epi32 _mm512_undefined_pd _mm512_undefined_ps _mm512_xor_epi32 _mm512_xor_epi64 _PGOPTI_Prof_Reset_All _xabort _xbegin _xend _xtest --sysroot compiler option --version compiler option -A compiler option -A- compiler option -alias-const compiler option -align compiler option -ansi compiler option -ansi-alias compiler option -ansi-alias-check compiler option -auto-ilp32 compiler option -auto-p32 compiler option -ax compiler option -B compiler option -Bdynamic compiler option -Bstatic compiler option -Bsymbolic compiler option -Bsymbolic-functions compiler option -c compiler option    Creating Libraries    c -C compiler option -check compiler option -check-pointers compiler option -check-pointers-dangling compiler option -check-pointers-undimensioned compiler option -check-uninit compiler option -cilk-serialize compiler option -clang-name compiler option (OS X*) -clangxx-name compiler option (OS X*) -complex-limited-range compiler option -cxxlib compiler option -D compiler option -dD compiler option -debug compiler option -diag compiler option -diag-disable compiler option -diag-disable sc compiler option    diag-enable sc, Qdiag-enable:sc    diag, Qdiag -diag-dump compiler option -diag-enable compiler option -diag-enable port-win compiler option -diag-enable sc compiler option    diag-enable sc, Qdiag-enable:sc    diag, Qdiag -diag-enable sc-enums compiler option -diag-enable sc-include compiler option -diag-enable sc-mode compiler option    diag-enable sc, Qdiag-enable:sc    diag, Qdiag -diag-enable sc-single-file compiler option -diag-enable sv-include compiler option -diag-error compiler option -diag-error-limit compiler option -diag-file compiler option -diag-file-append compiler option -diag-id-numbers compiler option -diag-once compiler option -diag-remark compiler option -diag-sc-dir compiler option -diag-warning compiler option -dM compiler option -dN compiler option -dryrun compiler option -dumpmachine compiler option -dumpversion compiler option -dynamic-linker compiler option (Linux* only) -dynamiclib compiler option    Creating Libraries    Using Intel Shared Libraries -dynamiclib compiler option (OS X* only) -E compiler option -early-template-check compiler option -EP compiler option -F compiler option -Fa compiler option -fabi-version compiler option -falias compiler option -falign-functions compiler option -falign-stack compiler option -fargument-alias compiler option -fargument-noalias-global compiler option -fasm-blocks compiler option -fast compiler option -fast-transcendentals compiler option -fasynchronous-unwind-tables compiler option -fblocks compiler option (OS X*) -fbuiltin compiler option -fcode-asm compiler option -fcommon compiler option -fdata-sections compiler option -fexceptions compiler option -fextend-arguments compiler option -ffnalias compiler option -ffreestanding compiler option -ffriend-injection compiler option -ffunction-sections compiler option -fgnu89-inline compiler option -fimf-absolute-error compiler option -fimf-accuracy-bits compiler option -fimf-arch-consistency compiler option -fimf-domain-exclusion compiler option -fimf-max-error compiler option -fimf-precision compiler option -finline compiler option -finline-functions compiler options -finline-limit compiler option -finstrument-functions compiler option -fjump-tables compiler option -fkeep-static-consts compiler option -fma compiler option -fmath-errno compiler option -fmerge-debug-strings compiler option -fminshared compiler option -fms-dialect compiler option    Porting Microsoft Windows* OS Code to Linux* OS or OS X*    fms-dialect -fmudflap compiler option -fno-asynchronous-unwind-tables compiler option -fno-gnu-keywords compiler option -fno-implicit-inline-templates compiler option -fno-implicit-templates compiler option -fno-operator-names compiler option -fno-rtti compiler option -fnon-call-exceptions compiler option -fnon-lvalue-assign compiler option -fomit-frame-pointer compiler option -fopenmp compiler option -fp compiler option -fp-model compiler option    fp-model, fp    how to use -fp-port compiler option -fp-speculation compiler option -fp-stack-check compiler option -fp-trap compiler option -fp-trap-all compiler option -fpack-struct compiler option -fpascal-strings compiler option -fpermissive compiler option -fpic compiler option    Creating Libraries    Using Intel Shared Libraries    fpic -fpie compiler option (Linux* only) -freg-struct-return compiler option -fshort-enums compiler option -fsource-asm compiler option -fstack-protector compiler option -fstack-protector-all compiler option -fstack-security-check compiler option -fstrict-aliasing compiler option -fsyntax-only compiler option -ftemplate-depth compiler option -ftls-model compiler option -ftrapuv compiler option -ftz compiler option    ftz, Qftz    Setting the FTZ and DAZ Flags -funroll-all-loops compiler option -funroll-loops compiler option -funsigned-bitfields compiler option -funsigned-char compiler option -fvar-tracking compiler option -fvar-tracking-assignments compiler option -fverbose-asm compiler option -fvisibility compiler option -fvisibility-inlines-hidden compiler option -fzero-initialized-in-bss compiler option -g compiler option -g0 compiler option -gcc compiler option -gcc-name compiler option -gcc-sys compiler option -gcc-version compiler option -gdwarf-2 compiler option -gdwarf-3 compiler option -global-hoist compiler option -grecord-gcc-switches compiler option (Linux* only) -guide compiler option -guide-data-trans compiler option -guide-file compiler option -guide-file-append compiler option -guide-opts compiler option -guide-par compiler option -guide-profile compiler option -guide-vec compiler option -gxx-name compiler option -H compiler option -help compiler option -help-pragma compiler option -I compiler option -icc compiler option -idirafter compiler option -imacros compiler option -inline-calloc compiler option -inline-factor compiler option -inline-forceinline compiler option -inline-level compiler option -inline-max-per-compile compiler option -inline-max-per-routine compiler option -inline-max-size compiler option -inline-max-total-size compiler option -inline-min-size compiler option -intel-extensions compiler option -ip compiler option -ip-no-inlining compiler option -ip-no-pinlining compiler option -ipo compiler option    Using IPO    ipo, Qipo -ipo-c compiler option -ipo-jobs compiler option -ipo-S compiler option -ipo-separate compiler option -ipp compiler option -iprefix compiler option -iquote compiler option -isystem compiler option -iwithprefix compiler option -iwithprefixbefore compiler option -Kc++ compiler option -l compiler option -L compiler option -m compiler option -M compiler option -m32 compiler option -m64 compiler option -malign-double compiler option -malign-mac68k compiler option -malign-natural compiler option -malign-power compiler option -map-opts compiler option -march compiler option -masm compiler option -mcmodel compiler option (Linux* only) -mcpu compiler option -MD compiler option -mdynamic-no-pic compiler option (OS X*) -MF compiler option -MG compiler option -minstruction compiler option -mkl compiler option -MM compiler option -MMD compiler option -mmic compiler option -MP compiler option -mp1 compiler option -MQ compiler option -mregparm compiler option -MT compiler option -mtune compiler option -multibyte-chars compiler option -multiple-processes compiler option -no-bss-init compiler option -no-libgcc compiler option -no-offload compiler option -nodefaultlibs compiler option -nolib-inline compiler option -nostartfiles compiler option -nostdinc++ compiler option -nostdlib compiler option -o compiler option -O compiler option -offload-attribute-target compiler option -offload-option compiler option -openmp compiler option -openmp option -openmp-lib compiler option    OpenMP* Source Compatibility and Interoperability with Other Compilers    openmp-lib, Qopenmp-lib -openmp-link compiler option -openmp-report compiler option -openmp-stubs compiler option -openmp-task compiler option -openmp-threadprivate compiler option -opt-args-in-regs compiler option -opt-block-factor compiler option -opt-calloc compiler option (Linux only) -opt-class-analysis compiler option -opt-jump-tables compiler option -opt-malloc-options compiler option -opt-matmul compiler option -opt-mem-layout-trans compiler option -opt-multi-version-aggressive compiler option -opt-prefetch compiler option -opt-ra-region-strategy compiler option -opt-report compiler option -opt-report-file compiler option -opt-report-help compiler option -opt-report-phase compiler option -opt-report-routine compiler option -opt-streaming-stores compiler option -opt-subscript-in-range compiler option -Os compiler option -p compiler option -P compiler option -par-affinity compiler option (Linux* only) -par-num-threads compiler option -par-report compiler option -par-runtime-control compiler option -par-schedule compiler option -par-threshold compiler option -parallel compiler option -parallel-source-info compiler option -pc compiler option -pch compiler option -pch-create compiler option -pch-dir compiler option -pch-use compiler option -pie compiler option (Linux* only) -pragma-optimization-level compiler option -prec-div compiler option -prec-sqrt compiler option -print-multi-lib compiler option -prof-data-order compiler options -prof-dir compiler option -prof-file compiler option -prof-func-groups compiler option -prof-func-order compiler options -prof-gen compiler option    prof-gen, Qprof-gen    Profile an Application -prof-gen:srcpos compiler option    Profile an Application    code coverage tool    test priorization tool -prof-hotness-threshold compiler option -prof-src-dir compiler option -prof-src-root compiler option -prof-src-root-cwd compiler option -prof-use compiler option    prof-use, Qprof-use    code coverage tool    profmerge utility -prof-value-profiling compiler option -profile-functions compiler option -profile-loops compiler option -profile-loops-report compiler option -pthread compiler option -qdiag-disable linking option -qdiag-enable linking option -qhelp linking option -Qinstall compiler option -Qlocation compiler option -Qoption compiler option -qp compiler option -rcd compiler option -regcall compiler option -restrict compiler option -S compiler option -save-temps compiler option -scalar-rep compiler option -shared compiler option    Creating Libraries    Using Intel Shared Libraries -shared compiler option (Linux* only) -shared-intel compiler option    shared-intel    Using Intel Shared Libraries -shared-libgcc compiler option -simd compiler option -sox compiler option -static compiler option (Linux* only) -static-intel compiler option -static-libgcc compiler option -staticlib compiler option (OS X* only) -std compiler option -strict-ansi compiler option -T compiler option (Linux* only) -tbb compiler option -tcheck compiler option (Linux* only) -tcollect compiler option -tcollect-filter compiler option -traceback compiler option -u compiler option -U compiler option -undef compiler option -unroll compiler option -unroll-aggressive compiler option -use-asm compiler option -use-clang-env compiler option (OS X*) -use-intel-optimized-headers compiler option -use-msasm compiler option -v compiler option -V compiler option -vec compiler option -vec-guard-write compiler option -vec-report compiler option -vec-threshold compiler option -w compiler option    w    w, W -Wa compiler option -Wabi compiler option -Wall compiler option -watch compiler option -Wbrief compiler option -Wcheck compiler option -Wcomment compiler option -Wcontext-limit compiler option -wd compiler option -Wdeprecated compiler option -we compiler option -Weffc++ compiler option -Werror compiler option -Werror-all compiler option -Wextra-tokens compiler option -Wformat compiler option -Wformat-security compiler option -Winline compiler option -Wl compiler option -Wmain compiler option -Wmissing-declarations compiler option -Wmissing-prototypes compiler option -wn compiler option -Wnon-virtual-dtor compiler option -wo compiler option -Wp compiler option -Wp64 compiler option -Wpointer-arith compiler option -Wpragma-once compiler option -wr compiler option -Wremarks compiler option -Wreorder compiler option -Wreturn-type compiler option -Wshadow compiler option -Wsign-compare compiler option -Wstrict-aliasing compiler option -Wstrict-prototypes compiler option -Wtrigraphs compiler option -Wuninitialized compiler option -Wunknown-pragmas compiler option -Wunused-function compiler option -Wunused-variable compiler option -ww compiler option -Wwrite-strings compiler option -x (type) compiler option -x compiler option -X compiler option -xHost compiler option -Xlinker compiler option -Zp compiler option .dpi file    test prioritization Tool    code coverage Tool    profmerge and proforder Tools .dyn file    test prioritization Tool    code coverage Tool    profmerge and proforder Tools .dyn files .spi file    test prioritization Tool    code coverage Tool *** /arch compiler option /bigobj compiler option /c compiler option /C compiler option /check compiler option /D compiler option /debug compiler option /E compiler option /EH compiler option /EP compiler option /F compiler option /Fa compiler option /FA compiler option /fast compiler option /FC compiler option /Fd compiler option /FD compiler option /Fe compiler option /FI compiler option /fixed compiler option /Fm compiler option /Fo compiler option /fp compiler option    fp-model, fp    how to use /Fp compiler option /Fr compiler option /FR compiler option /GA compiler option /Gd compiler option /Ge compiler option /Gf compiler option /GF compiler option /Gh compiler option /GH compiler option /Gm compiler option /Gr compiler option /GR compiler option /Gs compiler option /GS compiler option /GT compiler option /GX compiler option /Gy compiler option /Gz compiler option /GZ compiler option /H compiler option /help compiler option /homeparams compiler option /hotpatch compiler option /I compiler option /J compiler option /LD compiler option /link compiler option /MD compiler option /MP compiler option /MT compiler option /noBool compiler option /nologo compiler option /O compiler option /Oa compiler option    falias    Oa /Ob compiler option /Od compiler option /Oi compiler option /openmp compiler option /Os compiler option /Ot compiler option /Ow compiler option    ffnalias    Ow /Ox compiler option /Oy compiler option /P compiler option /QA compiler option /QA- compiler option /Qalias-args /Qalias-const compiler option /Qansi-alias compiler option /Qansi-alias-check compiler option /Qauto-ilp32 compiler option /Qax compiler option /Qcheck-pointers compiler option /Qcheck-pointers-dangling compiler option /Qcheck-pointers-undimensioned compiler option /Qcilk-serialize compiler option /Qcomplex-limited-range compiler option /Qcontext-limit compiler option /Qcov-dir compiler option /Qcov-file compiler option /Qcov-gen compiler option    Profile an Application    Qcov-gen    code coverage tool /Qcxx-features compiler option /QdD compiler option /Qdiag compiler option /Qdiag-disable compiler option /Qdiag-disable:sc compiler option    diag-enable sc, Qdiag-enable:sc    diag, Qdiag /Qdiag-dump compiler option /Qdiag-enable compiler option /Qdiag-enable:sc compiler option    diag-enable sc, Qdiag-enable:sc    diag, Qdiag /Qdiag-enable:sc-enums compiler option /Qdiag-enable:sc-include compiler option /Qdiag-enable:sc-mode compiler option    diag-enable sc, Qdiag-enable:sc    diag, Qdiag /Qdiag-enable:sc-single-file compiler option /Qdiag-enable:sv-include compiler option /Qdiag-error compiler option /Qdiag-error-limit compiler option /Qdiag-file compiler option /Qdiag-file-append compiler option /Qdiag-id-numbers compiler option /Qdiag-once compiler option /Qdiag-remark compiler option /Qdiag-sc-dir compiler option /Qdiag-warning compiler option /QdM compiler option /QdN compiler option /Qeffc++ compiler option /Qextend-arguments compiler option /Qfast-transcendentals compiler option /Qfma compiler option /Qfnalign compiler option /Qfnsplit compiler option /Qfp-port compiler option /Qfp-speculation compiler option /Qfp-stack-check compiler option /Qfp-trap compiler option /Qfp-trap-all compiler option /Qfreestanding compiler option /Qftz compiler option    ftz, Qftz    Setting the FTZ and DAZ Flags /Qgcc-dialect compiler option    Porting Linux* OS or OS X* Code to Windows* OS    Qgcc-dialect /Qglobal-hoist compiler option /Qguide compiler option /Qguide-data-trans compiler option /Qguide-file compiler option /Qguide-file-append compiler option /Qguide-opts compiler option /Qguide-par compiler option /Qguide-profile compiler option /Qguide-vec compiler option /QH compiler option /Qimf-absolute-error compiler option /Qimf-accuracy-bits compiler option /Qimf-arch-consistency compiler option /Qimf-domain-exclusion compiler option /Qimf-max-error compiler option /Qimf-precision compiler option /Qinline-calloc compiler option /Qinline-dllimport compiler option /Qinline-factor compiler option /Qinline-forceinline compiler option /Qinline-max-per-compile compiler option /Qinline-max-per-routine compiler option /Qinline-max-size compiler option /Qinline-max-total-size compiler option /Qinline-min-size compiler option /Qinstruction compiler option /Qinstrument-functions compiler option /Qintel-extensions compiler option /Qip compiler option /Qip-no-inlining compiler option /Qip-no-pinlining compiler option /Qipo compiler option    Using IPO    ipo, Qipo /Qipo-c compiler option /Qipo-jobs compiler option /Qipo-S compiler option /Qipo-separate compiler option /Qipp compiler option /Qkeep-static-consts compiler option /Qlocation compiler option /QM compiler option /Qmap-opts compiler option /QMD compiler option /QMF compiler option /QMG compiler option /Qmkl compiler option /QMM compiler option /QMMD compiler option /Qms compiler option /QMT compiler option /Qmultibyte-chars compiler option /Qnobss-init compiler option /Qoffload-attribute-target compiler option /Qopenmp compiler option /Qopenmp option /Qopenmp-lib compiler option    OpenMP* Source Compatibility and Interoperability with Other Compilers    openmp-lib, Qopenmp-lib /Qopenmp-report compiler option /Qopenmp-stubs compiler option /Qopenmp-task compiler option /Qopenmp-threadprivate compiler option /Qopt-args-in-regs compiler option /Qopt-block-factor compiler option /Qopt-class-analysis compiler option /Qopt-jump-tables compiler option /Qopt-matmul compiler option /Qopt-mem-layout-trans compiler option /Qopt-multi-version-aggressive compiler option /Qopt-prefetch compiler option /Qopt-ra-region-strategy compiler option /Qopt-report compiler option /Qopt-report-file compiler option /Qopt-report-help compiler option /Qopt-report-phase compiler option /Qopt-report-routine compiler option /Qopt-streaming-stores compiler option /Qopt-subscript-in-range compiler option /Qoption compiler option /Qpar-adjust-stack compiler option /Qpar-affinity compiler option /Qpar-num-threads compiler option /Qpar-report compiler option /Qpar-runtime-control compiler option /Qpar-schedule compiler option /Qpar-threshold compiler option /Qparallel compiler option /Qparallel-source-info compiler option /Qpatchable-addresses compiler option /Qpc compiler option /Qpchi compiler option /Qprec compiler option /Qprec-div compiler option /Qprec-sqrt compiler option /Qprof-data-order compiler option /Qprof-dir compiler option /Qprof-file compiler option /Qprof-func-order compiler option /Qprof-gen compiler option    prof-gen, Qprof-gen    Profile an Application /Qprof-gen:srcpos compiler option    Profile an Application    code coverage tool    test priorization tool /Qprof-hotness-threshold compiler option /Qprof-src-dir compiler option /Qprof-src-root compiler option /Qprof-src-root-cwd compiler option /Qprof-use compiler option    prof-use, Qprof-use    code coverage tool    profmerge utility /Qprof-value-profiling compiler option /Qprofile-functions compiler option /Qprofile-loops compiler option /Qprofile-loops-report compiler option /Qrcd compiler option /Qregcall compiler option /Qrestrict compiler option /Qsafeseh compiler option /Qsave-temps compiler option /Qscalar-rep compiler option /Qsfalign compiler option /Qsimd compiler option /Qsox compiler option /Qstd compiler option /Qtbb compiler option /Qtcheck compiler option /Qtcollect compiler option /Qtcollect-filter compiler option /Qtemplate-depth compiler option /Qtrapuv compiler option /Qunroll compiler option /Qunroll-aggressive compiler option /Quse-intel-optimized-headers compiler option /Quse-msasm-symbols compiler option /QV compiler option /Qvc compiler option /Qvec compiler option /Qvec-guard-write compiler option /Qvec-report compiler option /Qvec-threshold compiler option /Qvla compiler option /Qwd compiler option /Qwe compiler option /Qwn compiler option /Qwo compiler option /Qwr compiler option /Qww compiler option /Qx compiler option /QxHost compiler option /Qzero-initialized-in-bss compiler option /RTC compiler option /S compiler option /showIncludes compiler option /Tc compiler option /TC compiler option /Tp compiler option /TP compiler option /traceback compiler option /u compiler option /U compiler option /V compiler option /vd compiler option /vmb compiler option /vmg compiler option /vmm compiler option /vms compiler option /vmv compiler option /w compiler option /W compiler option /Wall compiler option /watch compiler option /Wcheck compiler option /Werror-all compiler option /WL compiler option /Wp64 compiler option /Wport compiler option /WX compiler option /X compiler option /Y- compiler option /Yc compiler option /Yd compiler option /Yu compiler option /Z7 compiler option /Za compiler option /Zc compiler option /Ze compiler option /Zg compiler option /Zi compiler option /ZI compiler option /Zl compiler option /Zp compiler option /Zs compiler option absolute error    fimf-absolute-error, Qimf-absolute-error    option defining for math library function results adding additional Options for Target Compilation, Target Linking, and Target Archiver adding additional Options for Target Linking advanced PGO options Advanced Vector Extensions    Intrinsics for Intel® Advanced Vector Extensions    arithmetic operations    bitwise logical operations    blend and conditional merge operations    compare operations    conversion operations    load operations    minimum and maximum operations    miscellaneous operations    overview       Overview: Intrinsics for Intel® Advanced Vector Extensions Instructions       Details of Intel® Advanced Vector Extensions Intrinsics    packed test operations    permute operations    shuffle operations    unpack and interleave operations    vector generation operations    vector typecasting operations Advanced Vector Extensions 2    Intrinsics for Arithmetic Operations    Intrinsics for Arithmetic Shift Operations    Intrinsics for Operations to Manipulate Integer Data at Bit-Granularity    Intrinsics for Bitwise Operations    Intrinsics for Blend Operations    Intrinsics for Broadcast Operations    Intrinsics for Compare Operations    Intrinsics for Fused Multiply Add Operations    Intrinsics for GATHER Operations    Intrinsics for Insert/Extract Operations    Intrinsics for Masked Load/Store Operations    Intrinsics for Logical Shift Operations    Intrinsics for Miscellaneous Operations    Overview: Intrinsics for Intel® Advanced Vector Extensions 2 Instructions    Intrinsics for Pack/Unpack Operations    Intrinsics for Packed Move with Extend Operations    Intrinsics for Permute Operations    Intrinsics for Shuffle Operations    arithmetic operations    arithmetic shift operations    bit manipulation operations    bitwise logical operations    blend operations    broadcast operations    compare operations    fused multiply-add (FMA) operations    GATHER operations    insert and extract operations    load and store operations    logical shift operations    miscellaneous operations    overview    pack and unpack operations    packed move operations    permute operations    shuffle operations affinity, OpenMP*, specifying aliasing    ffnalias    falias    option specifying assumption in functions    option specifying assumption in programs aligning data alloc ALLOCATABLE    code coverage Tool    Programming with Auto-parallelization    basic block    code coverage    data flow    visual presentation alternate compiler options alternate tools and locations ANSI/ISO standard    Conformance to the C Standard    Conformance to the C++ Standard APIs for coprocessor application tests applications    Redistributing Libraries When Deploying Applications    O    deploying    option specifying code optimization for ar tool Array Notations    C/C++ Extensions for Array Notations Programming Model    array declarations    array section    assignment maps    function maps    gather and scatter operations    multi-dimensional casting operations    operator maps    programming hints    reduction and shift operations assembler    Wa    use-asm, Quse-asm    option passing options to    option producing objects through assembler output file    masm    option specifying a dialect for assembly files    Specifying Assembly Files    naming assembly listing file    Fa    option specifying generation of asynchronous computation asynchronous data transfer attribute for placing variables and functions on coprocessor attribute, applying target auto parallelism    guide-par, Qguide-par    option setting guidance for auto-parallelism    guide, Qguide    option setting guidance for auto-parallelization    Auto-Parallelization Overview    enabling    environment variables    guidelines    overview    programming with Auto-parallelization    Language Support for Auto-parallelization    language support auto-parallelizer    Auto-Parallelization Overview    option controlling level of diagnostics for    option enabling generation of multithreaded code    option setting threshold for loops auto-vectorization    guide-vec, Qguide-vec    guide, Qguide    option setting guidance for       guide-vec, Qguide-vec       guide, Qguide auto-vectorization hints auto-vectorizer    Automatic Vectorization Overview    Using Automatic Vectorization    AVX    SSE    SSE2    SSE3    SSSE3    using autovectorization autovectorization of innermost loops avoid    Avoiding Mixed Data Type Arithmetic Expressions    inefficient data types    mixed arithmetic expressions AVX    Intrinsics for Intel® Advanced Vector Extensions    arithmetic operations    bitwise logical operations    blend and conditional merge operations    compare operations    conversion operations    load operations    minimum and maximum operations    miscellaneous operations    overview       Overview: Intrinsics for Intel® Advanced Vector Extensions Instructions       Details of Intel® Advanced Vector Extensions Intrinsics    packed test operations    permute operations    shuffle operations    unpack and interleave operations    vector generation operations    vector typecasting operations AVX2    Intrinsics for Arithmetic Operations    Intrinsics for Arithmetic Shift Operations    Intrinsics for Operations to Manipulate Integer Data at Bit-Granularity    Intrinsics for Bitwise Operations    Intrinsics for Blend Operations    Intrinsics for Broadcast Operations    Intrinsics for Compare Operations    Intrinsics for Fused Multiply Add Operations    Intrinsics for GATHER Operations    Intrinsics for Insert/Extract Operations    Intrinsics for Masked Load/Store Operations    Intrinsics for Logical Shift Operations    Intrinsics for Miscellaneous Operations    Overview: Intrinsics for Intel® Advanced Vector Extensions 2 Instructions    Intrinsics for Pack/Unpack Operations    Intrinsics for Packed Move with Extend Operations    Intrinsics for Permute Operations    Intrinsics for Shuffle Operations    arithmetic operations    arithmetic shift operations    bit manipulation operations    bitwise logical operations    blend operations    broadcast operations    compare operations    fused multiply-add (FMA) operations    GATHER operations    insert and extract operations    load and store operations    logical shift operations    miscellaneous operations    overview    pack and unpack operations    packed move operations    permute operations    shuffle operations Binary Floating-Point Conformance Library Functions    Function List    homogeneous general-computational operations    non-computational operations    nonhomogeneous general-computational operations    quiet-computational operations    signaling-computational operations building an application that runs natively on Intel® MIC Architecture C++0x    std, Qstd    option enabling support of C++11    std, Qstd    option enabling support of c99    std, Qstd    option enabling support of calling conventions capturing IPO output changing number of threads    OpenMP* Directives and Clauses Summary    summary table of checking    Checking the Floating-point Stack State    floating-point stacks    stacks Checking the Floating-point Stack State cilk grainsize Clang compiler    clang-name    option specifying name of Clang environment    use-clang-env    option enabling Clang++ compiler    clangxx-name    option specifying the name of Class Libraries    About Intel® Many Integrated Core (Intel® MIC) Class Libraries    C++ classes and SIMD operations    capabilities of C++ SIMD classes    conventions    details    floating-point vector classes       Arithmetic Operators       Cacheability Support Operators       Compare Operators       Conditional Select Operators for Fvec Classes       Constructors and Initialization       Conversions       Data Alignment       Debug Operations       Load and Store Operators       Logical Operators       Minimum and Maximum Operators       Move Mask Operators       Fvec Notation Conventions       Overview: Floating-point Vector Classes       Unpack Operators       arithmetic operators       cacheability support operators       compare operators       conditional select operators       constructors and initialization       conversions       data alignment       debug operators       load operators       logical operators       minimum and maximum operators       move mask operators       notation conventions       overview       store operators       unpack operators    Hardware and Software Requirements    integer vector classes       Addition and Subtraction Operators       Assignment Operator       Clear MMX™ State Operator       Comparison Operators       Conditional Select Operators       Conversions between Fvec and Ivec       Debug Operations       Integer Functions for Streaming SIMD Extensions       Overview: Integer Vector Classes       Logical Operators       Multiplication Operators       Pack Operators       Rules for Operators       Shift Operators       Unpack Operators       addition operators          Addition and Subtraction Operators          subtraction operators       assignment operator       clear MMX™ state operators       comparison operators       conditional select operators       conversions between fvec and ivec       debug operators          Debug Operations          element access operator          element assignment operators       functions for SSE       ivec classes       logical operators       multiplication operators       pack operators       rules for operators       shift operators       unpack operators    overview    Quick reference    syntax    terms class libraries, introducing Classes    Programming Example    programming example classes, C++ and Intel® Many Integrated Core (Intel® MIC) SIMD operations code    ax, Qax    m    arch    march    xHost, QxHost    x, Qx    Overview: Using a Pragma    Writing Target-Specific Code Using a Pragma    Writing Target-Specific Code with _Cilk_offload    Writing Code that Should Not Be Built for CPU-Only Execution    option generating feature-specific       ax, Qax       m    option generating feature-specific for Windows* OS    option generating for specified CPU    option generating specialized    option generating specialized and optimized    target-specific       Overview: Using a Pragma       Writing Target-Specific Code Using a Pragma       Writing Target-Specific Code with _Cilk_offload    writing only for offload or native builds code coverage tool    color scheme    dynamic counters in    exporting data    syntax of code example, offload code layout codecov tool    Qcov-gen    Qcov-dir    Qcov-file    option producing an instrumented file for    option specifying a directory for profiling output for    option specifying a file name for summary files for compilation phases compilation units    Developer Directed Inline Expansion of User Functions    option to prevent linking as shareable object compiler    Introducing the Intel® C++ Compiler    Related Information    overview       Introducing the Intel® C++ Compiler       Related Information compiler    Compilation Phases    compilation phases compiler command-line options    grecord-gcc-switches    option recording compiler directives    Automatic Vectorization Overview    for vectorization compiler information    Saving Compiler Information in Your Executable    saving in your executable compiler installation    Qinstall    option specifying root directory for compiler operation    About Building Native Intel® MIC Architecture Applications    building an application that runs natively on Intel® MIC Architecture compiler operation    Understanding File Extensions    Invoking the Intel® C++ Compiler    input files    invoking from the command line compiler option mapping tool compiler options    Alternate Compiler Options    Deprecated and Removed Compiler Options    Compiler Option Descriptions and General Rules    New Options    map-opts, Qmap-opts    sox, Qsox    Displaying Options Passed to Offload Compilation    Displaying Online Lists and Functional Groupings    alternate    deprecated and removed    general rules for    new    option mapping to equivalents    option saving in executable or object file    overview of descriptions of    to display informational lists       Displaying Options Passed to Offload Compilation       Displaying Online Lists and Functional Groupings compiler options    Compiler Options for Interoperability    Template Instantiation    Passing Options to the Linker    for interoperability    for templates    linker-related compiler options    Portability Options    Specifying Symbol Visibility Explicitly    for portability    for visibility compiler options    Using Compiler Options    Other Considerations    command-line syntax    for optimization    option categories    using compiler reports    Requesting Compiler Reports with the xi* Tools    requesting with xi* tools compilers    Multi-version Compiler Support    using multiple versions compilervars environment script compilervars.bat compilervars.csh compilervars.sh compiling    Other Considerations    gcc* code with Intel® C++ compiling large programs compiling with IPO complex operations    complex-limited-range, Qcomplex-limited-range    option enabling algebraic expansion of computing asynchronously conditional check    vec-guard-write, Qvec-guard-write    option performing in a vectorized loop conditional parallel region execution    Compiler Directed Inline Expansion of Functions    inline expansion configuration files console    watch    option displaying information to conventions    Notational Conventions    in the documentation correct usage of countable loop COS    Loop Constructs    correct usage of counters for dynamic profile    Resetting the Dynamic Profile Counters    Resetting Profile Information CPU    march    mtune    option generating code for specified    option performing optimizations for specified CPU dispatch CPU time    test prioritization Tool    Inline Function Expansion    DPI lists    for inline function expansion cpuid create libraries using IPO cross compilation    About Building Native Intel® MIC Architecture Applications    about data alignment data format    Programming with Auto-parallelization    High-Level Optimizations (HLO) Overview    Automatic Vectorization Overview    partitioning    prefetching    type data ordering optimization data transformation    guide-data-trans, Qguide-data-trans    guide, Qguide    option setting guidance for       guide-data-trans, Qguide-data-trans       guide, Qguide data types    Using Efficient Data Types    efficiency data, moving from one variable to another data, transferring asynchronously dataflow analysis DAZ flag debug information    Fd    g, Zi, Z7    gdwarf-2    gdwarf-3    in program database file    option generating full    option generating in DWARF 2 format    option generating in DWARF 3 format debug information, linking debugging    Linking Debug Information    option affecting information generated       debug (Windows* OS)       debug (Linux* OS and OS X*)    option specifying settings to enhance       debug (Windows* OS)       debug (Linux* OS and OS X*) denormal exceptions denormal numbers denormal results    ftz, Qftz    option flushing to zero denormalized numbers (IEEE*) denormalized numbers (IEEE*)    Special Values    NaN values denormals deploying applications deprecated compiler options diagnostic messages    diag, Qdiag    diag-enable sc, Qdiag-enable:sc    diag-once, Qdiag-once    diag-enable sc-include, Qdiag-enable:sc-include    diag-file, Qdiag-file    option affecting which are issued    option controlling auto-parallelizer    option controlling display of    option controlling OpenMP    option controlling static analysis       diag-enable sc, Qdiag-enable:sc       diag, Qdiag    option controlling vectorizer    option enabling or disabling    option issuing only once    option processing include files and source files for    option sending to file diagnostics    Programming Guidelines for Vectorization    Remarks, Warnings, and Errors dialog box    Guided Auto Parallelism Invocation dialog box    Options: Guided Auto Parallelism dialog box    Guided Auto Parallelism invocation    Options: Guided Auto Parallelism difference operators differential coverage directory    isystem    B    option adding to start of include path    option specifying for executables    option specifying for includes and libraries disabling    Compiler Directed Inline Expansion of Functions    inlining distributing applications dllimport functions    Qinline-dllimport    option controlling inlining of DO constructs    Loop Constructs    numbers Documentation    Notational Conventions    conventions for driver tool commands    v    dryrun    option specifying to show and execute    option specifying to show but not execute dual core thread affinity dumping profile information    Interval Profile Dumping    Dumping Profile Information dyn files    Dumping and Resetting Profile Information    Profile an Application    Dumping Profile Information dynamic information    Profile-Guided Optimizations Overview    dumping profile information    files    resetting profile counters       Resetting the Dynamic Profile Counters       Resetting Profile Information    threads dynamic libraries    dynamiclib    option invoking tool to generate dynamic linker    dynamic-linker    option specifying an alternate dynamic shared object    shared    option producing a dynamic-link libraries (DLLs)    MD    option searching for unresolved references in dynamic-linking of libraries    Bdynamic    option enabling ebp register    fomit-frame-pointer, Oy    option determining use in optimizations Eclipse* integration    Reusing Guided Auto Parallelism Configurations    Using Guided Auto Parallelism in the Eclipse* IDE    reusing Guided Auto-Parallelization settings    using Guided Auto-Parallelization Eclipse* integration    Adding the Compiler and Debugger to Eclipse*    Using Cheat Sheets    Excluding Source Files from a Build    Setting Options for a Project or File    adding the compiler and debugger    cheat sheets    excluding source files from build    setting options Eclipse* integration    Adding a C Source File    Building a Project    Creating a New Project    Exporting Makefiles    Project Types and Makefiles    Overview: Eclipse* Integration    Running a Project    Starting Eclipse*    adding a source file    building a project    creating a new project    exporting makefiles    makefiles    overview    running a project    starting Eclipse* projects efficiency efficient    Compiler Directed Inline Expansion of Functions    inlining efficient data types EMMS Instruction    The EMMS Instruction: Why You Need It    EMMS Usage Guidelines    about    using endian data    Intel Extension Routines to OpenMP*    Enabling Auto-parallelization    Dumping Profile Information    Loop Constructs    Interval Profile Dumping    OpenMP* Run-time Library Routines    OpenMP* Examples    Profile an Application    and OpenMP* extension routines    auto-parallelization    dumping profile information    for auto-parallelization    loop constructs    PROF_DUMP_INTERVAL    routines overriding    using OpenMP*    using profile-guided optimization Enter index keyword Enter index keyword    Balanced Affinity Type    Setting the Number of OpenMP* Threads on the Coprocessor environment variables    Equivalent Environment Variables    I/O proxy control    setting with compilervars file    using to control coprocessor's environment environment variables    Setting Environment Variables    for Linux* OS and OS X* environment variables    Managing Libraries    LD_LIBRARY_PATH environment, controlling coprocessor environment, controlling coprocessor's error messages error parser example, offload code exception handling    fexceptions    option generating table of exceptions    fnon-call-exceptions    option allowing trapping instructions to throw exclude code    code coverage Tool    code coverage tool execution environment routines execution flow execution mode exit(), calling from an oflload region explicit-shape arrays    test prioritization Tool    code coverage Tool    profmerge and proforder Tools    Dumping and Resetting Profile Information    Profile an Application    Dumping Profile Information    OpenMP* Run-time Library Routines    .dpi       test prioritization Tool       code coverage Tool       profmerge and proforder Tools    .dyn       test prioritization Tool       code coverage Tool       Dumping and Resetting Profile Information       Profile an Application       profmerge and proforder Tools       Dumping Profile Information    .spi       test prioritization Tool       code coverage Tool    OpenMP* header    pgopti.dpi    pgopti.spi    source extended control registers    Overview: Intrinsics for Managing Extended Processor States and Registers    Intrinsics for Reading and Writing the Content of Extended Control Registers    managing    reading    writing extended processor states    Overview: Intrinsics for Managing Extended Processor States and Registers    managing feature-specific code    ax, Qax    x, Qx    option generating    option generating and optimizing find device number of coprocessor find number of coprocessors float-to-integer conversion    rcd, Qrcd    option enabling fast float64 vector intrinsics    Double-precision Floating-point Vector Intrinsics    Intel® Streaming SIMD Extensions 3 floating-point array operation Floating-point array: Handling floating-point calculations    fp-model, fp    option controlling semantics of Floating-point environment    Floating-Point Environment    -fp-model compiler option    /fp compiler option    pragma fenv_access floating-point exceptions    Reducing the Impact of Denormal Exceptions    denormal exceptions floating-point numbers    Special Values    special values floating-point numbers    Floating-point Formats    formats for floating-point operations    fp-model, fp    fp-port, Qfp-port    option controlling semantics of    option rounding results of Floating-point Operations    Programming Tradeoffs in Floating-point Applications    programming tradeoffs Floating-point Optimizations    -fp-model compiler option floating-point precision    pc, Qpc    prec-div, Qprec-div    prec-sqrt, Qprec-sqrt    mp1, Qprec    option controlling for significand    option improving for divides    option improving for square root    option improving general floating-point stack    Floating-point Formats    option checking FMA instructions    fma, Qfma    option enabling format function security problems    Wformat-security    option issuing warning for FTZ flag Function annotations    Function Annotations and the SIMD Directive for Vectorization    declspec(align)    declspec(vector) function entry and exit points    finstrument-functions, Qinstrument-functions    option determining instrumentation of function expansion function grouping    prof-func-groups    option enabling or disabling function grouping optimization function order list function order lists function ordering optimization function preemption function profiling    p    option compiling and linking for function splitting    Qfnsplit    option enabling or disabling functions    falign-functions, Qfnalign    option aligning on byte boundary functions and data objects    offload-attribute-target, Qoffload-attribute-target    option flagging with offload attribute functions, placing on the coprocessor functions, shared fused multiply-add instructions    fma, Qfma    option enabling g++ compiler    gxx-name    option specifying name of g++* language extensions gcc C++ run-time libraries    idirafter    X    cxxlib    include file path    option adding a directory to second    option removing standard directories from    option specifying to link to gcc compiler    gcc-name    option specifying name of gcc*    Porting from GNU gcc* to Microsoft Visual C++*    porting from gcc* built-in functions gcc* compatibility gcc* considerations gcc* interoperability gcc* language extensions GCC* project    Updating a Project to Use the Intel® C++ Compiler    updating to use the Intel® C++ compiler general compiler directives    Programming with Auto-parallelization    Inline Function Expansion    Profile-Guided Optimizations Overview    Programming Guidelines for Vectorization    API Support Overview    for auto-parallelization    for inlining functions    for profile-guided optimization    for vectorization    profiling information global function symbols    Bsymbolic-functions    option binding references to shared library definitions global routines and data objects    offload-option    option specifying options to be used for a specified target and tool global symbols    Global Symbols and Visibility Attributes    option binding references to shared library definitions GNU C++ compatibility Guided Auto-Parallelization    Reusing Guided Auto Parallelism Configurations    reusing settings in Eclipse* guided auto parallelism    Using Guided Auto Parallelism    Guided Auto Parallelism Overview    messages overview    options    overview    using guided auto-parallelism    guide-file-append, Qguide-file-append    guide-file, Qguide-file    option appending output to a file    option sending output to file guided auto-parallelism messages    GAP Message (Diagnostic ID 30506)    GAP Message (Diagnostic ID 30513)    GAP Message (Diagnostic ID 30515)    GAP Message (Diagnostic ID 30519)    GAP Message (Diagnostic ID 30521)    GAP Message (Diagnostic ID 30522)    GAP Message (Diagnostic ID 30523)    GAP Message (Diagnostic ID 30525)    GAP Message (Diagnostic ID 30526)    GAP Message (Diagnostic ID 30528)    GAP Message (Diagnostic ID 30531)    GAP Message (Diagnostic ID 30532)    GAP Message (Diagnostic ID 30533)    GAP Message (Diagnostic ID 30534)    GAP Message (Diagnostic ID 30535)    GAP Message (Diagnostic ID 30536)    GAP Message (Diagnostic ID 30537)    GAP Message (Diagnostic ID 30538)    GAP Message (Diagnostic ID 30753)    GAP Message (Diagnostic ID 30754)    GAP Message (Diagnostic ID 30755)    GAP Message (Diagnostic ID 30756)    GAP Message (Diagnostic ID 30757)    GAP Message (Diagnostic ID 30758)    GAP Message (Diagnostic ID 30759)    GAP Message (Diagnostic ID 30760)    diagnostic id 30506    diagnostic id 30513    diagnostic id 30515    diagnostic id 30519    diagnostic id 30521    diagnostic id 30522    diagnostic id 30523    diagnostic id 30525    diagnostic id 30526    diagnostic id 30528    diagnostic id 30531    diagnostic id 30532    diagnostic id 30533    diagnostic id 30534    diagnostic id 30535    diagnostic id 30536    diagnostic id 30537    diagnostic id 30538    diagnostic id 30753    diagnostic id 30754 (Linux* only)    diagnostic id 30755    diagnostic id 30756    diagnostic id 30757    diagnostic id 30758    diagnostic id 30759    diagnostic id 30760 Guided Auto-Parallelization    Using Guided Auto Parallelism in the Eclipse* IDE    Eclipse* integration half-float conversion hardware lock elision heterogeneous application    Appending Linker Options    building heterogeneous application    Appending Archiver Options for Creating Libraries    building heterogeneous programming    Overview: Heterogeneous Programming    overview high performance programming    Profile-Guided Optimizations Overview    applications for high-level optimizer HLO hot patching    hotpatch    option preparing a routine for hotness threshold    prof-hotness-threshold, Qprof-hotness-threshold    option setting i/o on the coprocessor IA-32 architecture based applications    High-Level Optimizations (HLO) Overview    HLO IEEE Floating-point Standard IEEE*    Special Values    floating-point values image extraction tool include files initiating an offload inline function expansion    inline-level, Ob    option specifying level of inlining    Compiler Directed Inline Expansion of Functions    Profile-Guided Optimizations Overview    Developer Directed Inline Expansion of User Functions    Inline Function Expansion    compiler directed    developer directed    option disabling full and partial    option disabling partial    option forcing    option specifying lower limit for large routines    option specifying maximum size of function for    option specifying maximum times for a routine    option specifying maximum times for compilation unit    option specifying total size routine can grow    option specifying upper limit for small routine    preemption inlining options    inline-factor, Qinline-factor    option specifying percentage multiplier for input files input/output instrumentation    Dumping Profile Information    compilation    execution    feedback compilation    option enabling or disabling for specified functions    program instrumentation calls    profile-functions, Qprofile-functions    option inserting for function instrumentation calls    profile-loops-report, Qprofile-loops-report    profile-loops, Qprofile-loops    option generating report for loops    option inserting for loops integer vector intrinsics    Integer Vector Intrinsic    Intel® Streaming SIMD Extensions 3 Intel-provided libraries    shared-intel    static-intel    option linking dynamically    option linking statically Intel® 64 architecture based applications    High-Level Optimizations (HLO) Overview    HLO Intel® Cilk™ Plus    __cilkrts_get_nworkers    __cilkrts_get_total_workers    __cilkrts_get_worker_number    Set Worker Count    __cilkrts_set_param    Microsoft Foundation Classes and Intel® Cilk™ Plus Programs    Getting Started    C/C++ Extensions for Array Notations Programming Model    Cache Efficiency and Bandwidth    cilk_for    cilk_spawn    cilk_sync    Convert a C/C++ Program    Advanced Topic: How to Write a New Reducer    Resolving Data Races    Data Races    Deadlocks    Debugging Strategies    Elemental Functions    Exception Handling    Key Concepts    False Sharing    Glossary    Granularity    Introduction to Keywords    Introduction to Holders    Using Holders - An Example    Holder Syntax    General Interaction with OS Threads    Considerations for Using Locks    Holding a Lock Across a Strand Boundary    Locks Cause Determinancy Races    Lock Contention    Mapping Strands to Workers    Memory Allocation Bottlenecks    Optimize the Serial Program    Performance Considerations for Intel® Cilk™ Plus Programs    Common Performance Pitfalls    Safety, Correctness, and Performance    Using Reducers - More Examples    Reducer Library    Using Reducers - A Simple Example    How Reducers Work    Introduction to Reducers    Introduction to the Run Time System API    Serialization    Strands    Summary of Intel® Cilk™ Plus Language Features    Timing Programs and Program Segments    Using Other Tools with Intel® Cilk™ Plus Programs    Work and Span    __cilkrts_get_nworkers    __cilkrts_get_total_workers    __cilkrts_get_worker_number    __cilkrts_set_param       Set Worker Count       __cilkrts_set_param    and Microsoft Foundation Classes    array notations    C/C++ extensions for array notations    cache efficiency    cilk_for    cilk_spawn    cilk_sync    converting a program    custom reducers    data races       Resolving Data Races       Data Races    deadlocks    debugging    description    elemental functions       Getting Started       Elemental Functions    environment variable    exception handling    execution model    false sharing    getting started    glosssary    granularity    header file    holders       Introduction to Holders       Using Holders - An Example       Holder Syntax    interaction with OS threads    locks       Considerations for Using Locks       Holding a Lock Across a Strand Boundary       Locks Cause Determinancy Races       Lock Contention    mapping strands to workers    memory allocation    optimizing serial programs    performance considerations    performance pitfalls    reducer considerations    reducer examples    reducer library    reducers       Using Reducers - A Simple Example       How Reducers Work       Introduction to Reducers    Run Time System API    serialization    strands    summary of language features    timing for performance    using with other tools    work and span Intel® Cilk™ Plus    Introduction    introduction Intel® compatibility libraries for OpenMP* Intel® extension routines Intel® IEEE 754-2008 Binary Floating-Point Conformance Library    Overview: Intel® IEEE 754-2008 Binary Floating-Point Conformance Library    formatOf general-computational operations       formatOf General-Computational Operations Functions       from_hexstring       from_string       to_int32_int       to_int32_rnint       to_int32_xfloor       to_int64_floor       to_int64_rninta       to_int64_xceil       to_int64_xfloor       to_uint32_int       to_uint32_rninta       to_uint32_xceil       to_uint32_xfloor       add       binary32_to_binary64       binary64_to_binary32       div       fma       from_int32       from_int64       from_uint32       from_uint64       mul       sqrt       sub       to_hexstring       to_int32_ceil       to_int32_floor       to_int32_rninta       to_int32_xceil       to_int32_xint       to_int32_xrnint       to_int32_xrninta       to_int64_ceil       to_int64_int       to_int64_rnint       to_int64_xint       to_int64_xrnint       to_int64_xrninta       to_string       to_uint32_ceil       to_uint32_floor       to_uint32_rnint       to_uint32_xint       to_uint32_xrnint       to_uint32_xrninta       to_uint64_ceil       to_uint64_floor       to_uint64_int       to_uint64_rnint       to_uint64_rninta       to_uint64_xceil       to_uint64_xfloor       to_uint64_xint       to_uint64_xrnint       to_uint64_xrninta    homogeneous general-computational operations       Homogeneous General-Computational Operations Functions       round_integral_zero       ilogb       maxnum       maxnum_mag       minnum       minnum_mag       next_down       next_up       rem       round_integral_exact       round_integral_nearest_away       round_integral_nearest_even       round_integral_negative       round_integral_positive       scalbn    non-computational operations       Non-Computational Operations Functions       isNaN       isNormal       isSubnormal       lowerFlags       restoreFlags       saveModes       testFlags       testSavedFlags       totalOrderMag       class       defaultMode       getBinaryRoundingDirection       is754version1985       is754version2008       isCanonical       isFinite       isInfinite       isSignaling       isSignMinus       isZero       radix       raiseFlags       restoreModes       saveFlags       setBinaryRoundingDirection       totalOrder    quiet-computational operations       Quiet-Computational Operations Functions       copy       negate       copysign    signaling-computational operations       Signaling-Computational Operations Functions       signaling_greater_equal       quiet_equal       quiet_greater       quiet_greater_equal       quiet_greater_unordered       quiet_less       quiet_less_equal       quiet_less_unordered       quiet_not_equal       quiet_not_greater       quiet_not_less       quiet_ordered       quiet_unordered       signaling_equal       signaling_greater       signaling_greater_unordered       signaling_less       signaling_less_ unordered       signaling_less_equal       signaling_not_equal       signaling_not_greater       signaling_not_less    using the library Intel® IPP libraries    ipp, Qipp    option letting you link to Intel® linking tools Intel® MIC Architecture Intel® MIC Architecture application    mmic    option building native Intel® MIC Architecture features    offload-attribute-target, Qoffload-attribute-target    option flagging with offload attribute Intel® MKL    mkl, Qmkl    option letting you link to Intel® TBB libraries    tbb, Qtbb    option letting you link to Intel® Trace Collector API    tcollect, Qtcollect    option inserting probes to call Intel® AVX Intrinsic    _mm256_stream_si256    _mm256_stream_si256 (VMOVNTDQ) Intel® C/C++ Error Parser Intel® C++ project    Updating a Project to Use the Intel® C++ Compiler    updating to use current compiler version Intel® Hyper-Threading Technology    Enabling Further Loop Parallelization for Multicore Platforms    parallel loops    thread pools Intel® Many Integrated Core (Intel® MIC) Class Libraries Intel® MIC Architecture    Allocating Memory for Parts of Arrays    Moving Data from One Variable to Another    Overview: Intel® MIC Architecture    allocating memory for parts of arrays    moving data from one variable to another    overview Intel® SSE4 intrinsics    Application Targeted Accelerators Intrinsics    Floating Point Dot Product Intrinsics    application targeted accelerator intrinsics    intrinsics Intel® Streaming SIMD Extensions    Cacheability Support Intrinsics    Compare Intrinsics    Conversion Intrinsics    Details about Intel® Streaming SIMD Extensions Intrinsics    Integer Intrinsics    Load Intrinsics    Logical Intrinsics    Macro Function for Matrix Transposition    Macro Functions to Read and Write Control Registers    Macro Function for Shuffle Operations    Miscellaneous Intrinsics    Overview: Intel® Streaming SIMD Extensions    Writing Programs with Intel® Streaming SIMD Extensions Intrinsics    Set Intrinsics    Store Intrinsics    cacheability support operations    compare operations    conversion operations    data types    integer operations    load operations    logical operations    macro functions       Macro Function for Matrix Transposition       Macro Functions to Read and Write Control Registers       Macro Function for Shuffle Operations       matrix transposition       shuffle function          Macro Functions to Read and Write Control Registers          Macro Function for Shuffle Operations    miscellaneous operations    overview    programming with Intel® SSE intrinsics    registers    set operations    store operations Intel® Streaming SIMD Extensions 2    Cacheability Support Intrinsics    Casting Support Intrinsics    Arithmetic Intrinsics    Compare Intrinsics    Conversion Intrinsics    Load Intrinsics    Logical Intrinsics    Set Intrinsics    Store Intrinsics    Arithmetic Intrinsics    Compare Intrinsics    Conversion Intrinsics    Load Intrinsics    Logical Intrinsics    Move Intrinsics    Set Intrinsics    Shift Intrinsics    Store Intrinsics    Miscellaneous Intrinsics    Overview: Intel® Streaming SIMD Extensions 2 (Intel® SSE2)    Pause Intrinsic    Macro Function for Shuffle    cacheability support intrinsics    casting support intrinsics    FP arithmetic intrinsics    FP compare intrinsics    FP conversion intrinsics    FP load intrinsics    FP logical intrinsics    FP set intrinsics    FP store intrinsics    integer arithmetic intrinsics    integer compare intrinsics    integer conversion intrinsics    integer load intrinsics    integer logical intrinsics    integer move intrinsics    integer set intrinsics    integer shift intrinsics    integer store intrinsics    miscellaneous intrinsics    overview    pause intrinsic    shuffle macro Intel® Streaming SIMD Extensions 3    Macro Functions    Overview: Intel® Streaming SIMD Extensions 3 (Intel® SSE3)    macro functions    overview Intel® Streaming SIMD Extensions 4    Application Targeted Accelerators Intrinsics    Cacheability Support Intrinsic    Floating Point Rounding Intrinsics    Floating Point Dot Product Intrinsics    Packed Blending Intrinsics    Packed Compare for Equal Intrinsic    Packed Compare Intrinsics    Packed DWORD to Unsigned WORD Intrinsic    Packed Format Conversion Intrinsics    Packed Integer Min/Max Intrinsics    Register Insertion/Extraction Intrinsics    DWORD Multiply Intrinsics    Test Intrinsics    application targeted accelerator intrinsics    cacheability support intrinsic    floating-point rounding intrinsics    FP dot product intrinsics    packed blending intrinsics    packed compare for equal intrinsic    packed compare intrinsics    packed DWORD to unsigned WORD intrinsic    packed format conversion intrinsics    packed integer min/max intrinsics    register insertion/extraction intrinsics    test intrinsics       DWORD Multiply Intrinsics       Test Intrinsics Intel® Streaming SIMD Extensions4    Overview: Intel® Streaming SIMD Extensions 4 (Intel® SSE4)    overview intermediate files    save-temps, Qsave-temps    option saving during compilation intermediate representation (IR)    Using IPO    Interprocedural Optimization (IPO) Overview interoperability    gcc Interoperability    with g++*    with gcc* interoperability options interprocedural optimizations    Compiler Directed Inline Expansion of Functions    Profile-Guided Optimizations Overview    capturing intermediate output    code layout    compilation    compiling    considerations    creating libraries    initiating    issues    large programs    linking       Using IPO       Interprocedural Optimization (IPO) Overview    option enabling additional    option enabling between files    option enabling for single file compilation    overview    performance    using    whole program analysis    xiar    xild    xilibtool into intrinsics    Intrinsics Returning Vectors of Undefined Values    Overview: Intrinsics Reference    Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions    Overview: Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions    Floating-point Intrinsics    Integer Arithmetic Intrinsics    Miscellaneous Intrinsics    Overview: Intrinsics across Intel Architectures    String and Block Copy Intrinsics    Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly    Alignment Support    Details about Intrinsics    Intrinsics for Saving and Restoring the Extended Processor States    Intrinsics for Managing Extended Processor States and Registers    Intrinsics for Reading and Writing the Content of Extended Control Registers    Intrinsics for Converting Half Floats    Overview: Intrinsics to Convert Half Float Types    Inline Assembly    Intrinsics for Intel® Post-32nm Processor Instruction Extensions    Intrinsics for Intel® Advanced Vector Extensions    Intrinsics for Intel® Advanced Vector Extensions 2    Conversion Intrinsics    Arithmetic Intrinsics    Cacheability Support Intrinsics    Compare Intrinsics    Details about Intel® Streaming SIMD Extensions Intrinsics    Integer Intrinsics    Logical Intrinsics    Macro Function for Matrix Transposition    Macro Functions to Read and Write Control Registers    Macro Function for Shuffle Operations    Miscellaneous Intrinsics    Overview: Intel® Streaming SIMD Extensions    Writing Programs with Intel® Streaming SIMD Extensions Intrinsics    Set Intrinsics    Store Intrinsics    Cacheability Support Intrinsics    Casting Support Intrinsics    Arithmetic Intrinsics    Compare Intrinsics    Conversion Intrinsics    Load Intrinsics    Logical Intrinsics    Set Intrinsics    Store Intrinsics    Arithmetic Intrinsics    Compare Intrinsics    Conversion Intrinsics    Load Intrinsics    Logical Intrinsics    Move Intrinsics    Set Intrinsics    Shift Intrinsics    Store Intrinsics    Miscellaneous Intrinsics    Overview: Intel® Streaming SIMD Extensions 2 (Intel® SSE2)    Pause Intrinsic    Macro Function for Shuffle    Single-precision Floating-point Vector Intrinsics    Double-precision Floating-point Vector Intrinsics    Integer Vector Intrinsic    Macro Functions    Miscellaneous Intrinsics    Overview: Intel® Streaming SIMD Extensions 3 (Intel® SSE3)    Application Targeted Accelerators Intrinsics    Cacheability Support Intrinsic    DWORD Multiply Intrinsics    Floating Point Rounding Intrinsics    Floating Point Dot Product Intrinsics    Overview: Intel® Streaming SIMD Extensions 4 (Intel® SSE4)    Packed Blending Intrinsics    Packed Compare for Equal Intrinsic    Packed Compare Intrinsics    Packed DWORD to Unsigned WORD Intrinsic    Packed Format Conversion Intrinsics    Packed Integer Min/Max Intrinsics    Register Insertion/Extraction Intrinsics    Test Intrinsics    Allocating and Freeing Aligned Memory Blocks    MMX™ Technology Compare Intrinsics    Details about MMX™ Technology Intrinsics    The EMMS Instruction: Why You Need It    EMMS Usage Guidelines    MMX™ Technology General Support Intrinsics    MMX™ Technology Logical Intrinsics    Overview: MMX™ Technology Intrinsics    MMX™ Technology Packed Arithmetic Intrinsics    MMX™ Technology Set Intrinsics    MMX™ Technology Shift Intrinsics    Naming and Usage Syntax    Absolute Value Intrinsics    Addition Intrinsics    Concatenate Intrinsics    Multiplication Intrinsics    Negation Intrinsics    Overview: Supplemental Streaming SIMD Extensions 3 (SSSE3)    Shuffle Intrinsics    Subtraction Intrinsics    _mm_cexp_ps, _mm256_cexp_ps    _mm_clog_ps, _mm256_clog_ps    _mm_csqrt_ps, _mm256_csqrt_ps    _mm_cdfnorminv_pd, _mm256_cdfnorminv_pd    _mm_cdfnorminv_ps, _mm256_cdfnorminv_ps    _mm_erf_pd, _mm256_erf_pd    _mm_erf_ps, _mm256_erf_ps    _mm_erfc_pd, _mm256_erfc_pd    _mm_erfc_ps, _mm256_erfc_ps    _mm_erfinv_pd, _mm256_erfinv_pd    _mm_erfinv_ps, _mm256_erfinv_ps    _mm_exp2_pd, _mm256_exp2_pd    _mm_exp2_ps, _mm256_exp2_ps    _mm_hypot_ps, _mm256_hypot_ps    _mm_exp_pd, _mm256_exp_pd    _mm_exp_ps, _mm256_exp_ps    _mm_exp10_pd, _mm256_exp10_pd    _mm_exp10_ps, _mm256_exp10_ps    _mm_expm1_pd, _mm256_expm1_pd    _mm_expm1_ps, _mm256_expm1_ps    _mm_hypot_pd, _mm256_hypot_pd    _mm_pow_pd, _mm256_pow_pd    _mm_pow_ps, _mm256_pow_ps    _mm_log_pd, _mm256_log_pd    _mm_log_ps, _mm256_log_ps    _mm_log10_pd, _mm256_log10_pd    _mm_log10_ps, _mm256_log10_ps    _mm_log1p_pd, _mm256_log1p_pd    _mm_log1p_ps, _mm256_log1p_ps    _mm_log2_pd, _mm256_log2_pd    _mm_log2_ps, _mm256_log2_ps    _mm_logb_pd, _mm256_logb_pd    _mm_logb_ps, _mm256_logb_ps    Overview: Intrinsics for Short Vector Math Library (SVML) Functions    _mm_sqrt_ps, _mm256_sqrt_ps    _mm_cbrt_pd, _mm256_cbrt_pd    _mm_cbrt_ps, _mm256_cbrt_ps    _mm_invcbrt_pd, _mm256_invcbrt_pd    _mm_invcbrt_ps, _mm256_invcbrt_ps    _mm_invsqrt_pd, _mm256_invsqrt_pd    _mm_invsqrt_ps, _mm256_invsqrt_ps    _mm_sqrt_pd, _mm256_sqrt_pd    _mm_sinh_ps, _mm256_sinh_ps    _mm_acos_pd, _mm256_acos_pd    _mm_acos_ps, _mm256_acos_ps    _mm_acosh_pd, _mm256_acosh_pd    _mm_acosh_ps, _mm256_acosh_ps    _mm_asin_pd, _mm256_asin_pd    _mm_asin_ps, _mm256_asin_ps    _mm_asinh_pd, _mm256_asinh_pd    _mm_asinh_ps, _mm256_asinh_ps    _mm_atan_pd, _mm256_atan_pd    _mm_atan_ps, _mm256_atan_ps    _mm_atan2_pd, _mm256_atan2_pd    _mm_atan2_ps, _mm256_atan2_ps    _mm_atanh_pd, _mm256_atanh_pd    _mm_atanh_ps, _mm256_atanh_ps    _mm_cos_pd, _mm256_cos_pd    _mm_cos_ps, _mm256_cos_ps    _mm_cosd_pd, _mm256_cosd_pd    _mm_cosd_ps, _mm256_cosd_ps    _mm_cosh_pd, _mm256_cosh_pd    _mm_cosh_ps, _mm256_cosh_ps    _mm_sin_pd, _mm256_sin_pd    _mm_sin_ps, _mm256_sin_ps    _mm_sincos_pd, _mm256_sincos_pd    _mm_sincos_ps, _mm256_sincos_ps    _mm_sind_pd, _mm256_sind_pd    _mm_sind_ps, _mm256_sind_ps    _mm_sinh_pd, _mm256_sinh_pd    _mm_tan_pd, _mm256_tan_pd    _mm_tan_ps, _mm256_tan_ps    _mm_tand_pd, _mm256_tand_pd    _mm_tand_ps, _mm256_tand_ps    _mm_tanh_pd, _mm256_tanh_pd    _mm_tanh_ps, _mm256_tanh_ps    Intel® SSE2       Intrinsics Returning Vectors of Undefined Values       intrinsics returning vectors of undefined values          Intrinsics Returning Vectors of Undefined Values          _mm_undefined_pd()          _mm_undefined_ps()          _mm_undefined_si128()    about    Advanced Encryption Standard (AES) Implementation       Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions       Overview: Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions       _mm_aesdec_si128       _mm_aesdeclast_si128       _mm_aesenc_si128       _mm_aesenclast_si128       _mm_aesimc_si128       _mm_aeskeygenassist_si128       overview    All Intel Architectures       Floating-point Intrinsics       Integer Arithmetic Intrinsics       Miscellaneous Intrinsics       Overview: Intrinsics across Intel Architectures       String and Block Copy Intrinsics       floating point operations       integer arithmetic operations       miscellaneous operations       overview       string and block copy operations    carry-less multiplication instruction       Overview: Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions       _mm_clmulepi64_si128    data alignment       Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly       Alignment Support    data types    extended processor states       Intrinsics for Saving and Restoring the Extended Processor States       restoring       saving    for managing extended processor states and registers       Intrinsics for Managing Extended Processor States and Registers       Intrinsics for Reading and Writing the Content of Extended Control Registers       _fxrstor()       _fxrstor64()       _fxsave()       _fxsave64()       _xgetbv()       _xrstor()       _xrstor64()       _xsave()       _xsave64()       _xsaveopt()       _xsaveopt64()       _xsetbv()       restoring extended processor states       saving extended processor states    half-float conversion       Intrinsics for Converting Half Floats       Overview: Intrinsics to Convert Half Float Types       _cvtsh_ss       _cvtss_sh       _mm_cvtph_ps       _mm_cvtps_ph       overview    inline assembly       Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly       Inline Assembly    Intel® Post-32nm Processor Instruction Extensions       Intrinsics for Intel® Post-32nm Processor Instruction Extensions       _rdrand16_step()       _rdrand32_step()       _rdrand64_step()       base registers          Intrinsics that Allow Reading from and Writing to the FS Base and GS Base Registers          _readfsbase_u32()          _readfsbase_u64()          _readgsbase_u32()          _readgsbase_u64()          _writefsbase_u32()          _writefsbase_u64()          _writegsbase_u32()          _writegsbase_u64()       half-float          _mm_cvtph_ps()          Intrinsics for Converting Half Floats that Map to Intel® Post-32nm Processor Instructions          _mm_cvtps_ph()          _mm256_cvtph_ps()          _mm256_cvtps_ph()          conversion             _mm_cvtph_ps()             Intrinsics for Converting Half Floats that Map to Intel® Post-32nm Processor Instructions             _mm_cvtps_ph()             _mm256_cvtph_ps()             _mm256_cvtps_ph()             _mm_cvtph_ps()                _mm_cvtph_ps()                Intrinsics for Converting Half Floats that Map to Intel® Post-32nm Processor Instructions             _mm_cvtps_ph()             _mm_cvtps_ph())             _mm256_cvtph_ps()                Intrinsics for Converting Half Floats that Map to Intel® Post-32nm Processor Instructions                _mm256_cvtph_ps()             _mm256_cvtps_ph()                Intrinsics for Converting Half Floats that Map to Intel® Post-32nm Processor Instructions                _mm256_cvtps_ph()       overview       random number generation (RDRAND)    Intel® AVX       Intrinsics for Intel® Advanced Vector Extensions       arithmetic intrinsics          _mm256_hadd_ps          _mm256_addsub_pd          _mm256_addsub_ps          _mm256_div_pd          _mm256_div_ps          _mm256_dp_ps          _mm256_hadd_pd          _mm256_hsub_pd          _mm256_hsub_ps          _mm256_mul_pd          _mm256_mul_ps          _mm256_rcp_ps          _mm256_rsqrt_ps          _mm256_sqrt_pd          _mm256_sqrt_ps          _mm256_hadd_ps          _mm256_addsub_pd (VADDSUBPD)          _mm256_addsub_ps (VADDSUBPS)          _mm256_div_pd (VDIVPD)          _mm256_div_ps (VDIVPS)          _mm256_dp_ps (VDPPS)          _mm256_hadd_pd (VHADDPD)          _mm256_hsub_pd (VHSUBPD)          _mm256_hsub_ps (VHSUBPS)          _mm256_mul_pd (VMULPD)          _mm256_mul_ps (VMULPS)          _mm256_rcp_pd (VRCPPS)          _mm256_rsqrt_ps (VRSQRTPS)          _mm256_sqrt_pd (VSQRTPD)          _mm256_sqrt_ps (VSQRTPS)       arithmetic operations          Intrinsics for Arithmetic Operations          _mm256_add_pd (VADDPD)          _mm256_add_ps (VADDPS)          _mm256_sub_pd (VSUBPD)          _mm256_sub_ps (VSUBPS)       bitwise logical operations       bitwise operations          _mm256_and_pd          _mm256_and_ps          _mm256_andnot_pd          _mm256_andnot_ps          _mm256_or_pd          _mm256_or_ps          _mm256_xor_pd          _mm256_xor_ps          __mm256_and_pd (VANDPD)          _mm256_and_ps (VANDPS)          _mm256_andnot_pd (VANDNPD)          _mm256_andnot_ps (VANDNPS)          _mm256_or_pd (VORPD)          _mm256_or_ps (VORPS)          _mm256_xor_pd (VXORPD)          _mm256_xor_ps (VXORPS)       blend and conditional merge operations          Intrinsics for Blend and Conditional Merge Operations          _mm256_blendv_ps (VBLENDVPS)          _mm256_blend_pd (VBLENDPD)          _mm256_blend_ps (VBLENDPS)          _mm256_blendv_pd (VBLENDVPD)       compare operations          Intrinsics for Compare Operations          _m256_cmp_pd (VCMPPD)          _m256_cmp_ps (VCMPPS)          _mm_cmp_pd (VCMPPD)          _mm_cmp_ps (VCMPPS)          _mm_cmp_sd (VCMPSD)          _mm_cmp_ss (VCMPSS)       conversion operations          Intrinsics for Conversion Operations          _m256_cvtps_epi32 (VCVTPS2DQ)          _m256_cvtps_pd (VCVTPS2PD)          _mm256_cvtepi32_pd (VCVTDQ2PD)          _mm256_cvtepi32_ps (VCVTDQ2PS)          _mm256_cvtpd_epi32 (VCVTPD2DQ)          _mm256_cvtpd_ps (VCVTPD2PS)          _mm256_cvttpd_epi32 (VCVTTPD2DQ)          _mm256_cvttps_epi32 (VCVTTPS2DQ)       load operations          Intrinsics for Load Operations          _mm_broadcast_ss (VBROADCASTSS)          _mm_maskload_pd (VMASKMOVPD)          _mm_maskstore_ps (VMASKMOVPS)          _mm256_broadcast_pd (VBROADCASTF128)          _mm256_broadcast_ps (VBROADCASTF128)          _mm256_broadcast_sd (VBROADCASTSD)          _mm256_broadcast_ss (VBROADCASTSS)          _mm256_load_pd (VMOVAPD)          _mm256_load_ps (VMOVAPS)          _mm256_load_si256 (VMOVDQA)          _mm256_loadu_pd (VMOVUPD)          _mm256_loadu_ps (VMOVUPS)          _mm256_loadu_si256 (VMOVDQU)          _mm256_maskload_pd (VMASKMOVPD)          _mm256_maskstore_ps (VMASKMOVPS)          _mm256_store_pd (VMOVAPD)          _mm256_store_ps (VMOVAPS)          _mm256_store_si256 (VMOVDQA)          _mm256_storeu_pd (VMOVUPD)          _mm256_storeu_ps (VMOVUPS)          _mm256_storeu_si256 (VMOVDQU)          _mm256_stream_pd (VMOVNTPD)          _mm256_stream_ps (VMOVNTPS)       load operations          _mm256_maskload_ps, _mm_maskload_ps          _mm256_maskstore_pd, _mm_maskstore_pd          _mm_maskload_ps (VMASKMOVPS)          _mm_maskstore_pd (VMASKMOVPD)          _mm256_add_ps (VMASKMOVPS)          _mm256_maskstore_pd (VMASKMOVPD)       minimum and maximum operations       miscellaneous operations          Intrinsics for Miscellaneous Operations          _mm256_extractf128_pd (VEXTRACTF128)          _mm256_extractf128_ps (VEXTRACTF128)          _mm256_extractf128_si256 (VEXTRACTF128)          _mm256_insertf128_pd (VINSERTF128)          _mm256_insertf128_ps (VINSERTF128)          _mm256_insertf128_si256 (VINSERTF128)          _mm256_lddqu_si256 (VLDDQU)          _mm256_movedup_pd (VMOVDDUP)          _mm256_movehdup_ps (VMOVSHDUP)          _mm256_moveldup_ps (VMOVSLDUP)          _mm256_movemask_pd (VMOVMSKPD)          _mm256_movemask_ps (VMOVMSKPS)          _mm256_round_pd (VROUNDPD)          _mm256_round_ps (VROUNDPS)          _mm256_set_epi32          _mm256_set_pd          _mm256_set_ps          _mm256_set1_epi32          _mm256_set1_pd          _mm256_set1_ps          _mm256_setr_epi32          _mm256_setr_pd          _mm256_setr_ps          _mm256_setzero_pd          _mm256_setzero_ps          _mm256_setzero_si256          _mm256_zeroall (VZEROALL)          _mm256_zeroupper (VZEROUPPER)       operations returning vectors of undefined values          _mm256_undefined_pd()          _mm256_undefined_ps()          _mm256_undefined_si128          _mm256_undefined_pd()          _mm256_undefined_ps()          _mm256_undefined_si128       operations to determine maximum value          _mm256_max_pd          _mm256_max_ps          _mm256_max_pd (VMAXPD)          _mm256_max_ps (VMAXPS)       operations to determine minimum value          _mm256_min_pd          _mm256_min_ps          _mm256_min_pd (VMINPD)          _mm256_min_ps (VMINPS)       overview          Overview: Intrinsics for Intel® Advanced Vector Extensions Instructions          Details of Intel® Advanced Vector Extensions Intrinsics       packed test operations          Intrinsics for Packed Test Operations          _mm_testc_pd (VTESTPD)          _mm_testc_ps (VTESTPS)          _mm_testnzc_pd (VTESTPD)          _mm_testnzc_ps (VTESTPS)          _mm_testz_pd (VTESTPD)          _mm_testz_ps (VTESTPS)          _mm256_testc_pd (VTESTPD)          _mm256_testc_ps (VTESTPS)          _mm256_testc_si256 (VPTEST)          _mm256_testnzc_pd (VTESTPD)          _mm256_testnzc_ps (VTESTPS)          _mm256_testnzc_si256 (VPTEST)          _mm256_testz_pd (VTESTPD)          _mm256_testz_ps (VTESTPS)          _mm256_testz_si256 (VPTEST)       permute operations          Intrinsics for Permute Operations          _mm_permute_pd (VPERMILPD)          _mm_permute_ps (VPERMILPS)          _mm_permutevar_pd (VPERMILPD)          _mm_permutevar_ps (VPERMILPS)          _mm256_permute_pd (VPERMILPD)          _mm256_permute_ps (VPERMILPS)          _mm256_permute2f128_pd (VPERM2F128)          _mm256_permute2f128_ps (VPERM2F128)          _mm256_permute2f128_si256 (VPERM2F128)          _mm256_permutevar_pd (VPERMILPD)          _mm256_permutevar_ps (VPERMILPS)       shuffle operations          Intrinsics for Shuffle Operations          _mm256_shuffle_pd (VSHUFPD)          _mm256_shuffle_ps (VSHUFPS)       unpack and interleave operations          Intrinsics for Unpack and Interleave Operations          _mm256_unpackhi_pd (VUNPCKHPD)          _mm256_unpackhi_ps (VUNPCKHPS)          _mm256_unpacklo_pd (VUNPCKLPD)          _mm256_unpacklo_ps (VUNPCKLPS)       vector generation operations       vector typecasting operations          Support Intrinsics for Vector Typecasting Operations          _mm256_castpd_ps          _mm256_castpd_si256          _mm256_castpd128_pd256          _mm256_castpd256_pd128          _mm256_castps_pd          _mm256_castps_si256          _mm256_castps128_ps256          _mm256_castps256_ps128          _mm256_castsi128_si256          _mm256_castsi256_pd          _mm256_castsi256_ps          _mm256_castsi256_si128    Intel® AVX2       Intrinsics for Intel® Advanced Vector Extensions 2       arithmetic operations          Intrinsics for Arithmetic Operations          _mm256_abs_epi16 (VPABSW)          _mm256_abs_epi32 (VPABSD)          _mm256_abs_epi8 (VPABSB)          _mm256_add_epi16 (VPADDW)          _mm256_add_epi32 (VPADDD)          _mm256_add_epi64 (VPADDQ)          _mm256_add_epi8 (VPADDB)          _mm256_adds_epi16 (VPADDSW)          _mm256_adds_epi8 (VPADDSB)          _mm256_adds_epu16 (VPADDUSW)          _mm256_adds_epu8 (VPADDUSB)          _mm256_avg_epu16 (VPAVGW)          _mm256_avg_epu8 (VPAVGB)          _mm256_hadd_epi16 (VPHADDW)          _mm256_hadd_epi32 (VPHADDD)          _mm256_hadds_epi16 (VPHADDSW)          _mm256_hsub_epi16 (VPHSUBW)          _mm256_hsub_epi32 (VPHSUBD)          _mm256_hsubs_epi16 (VPHSUBSW)          _mm256_madd_epi16 (VPMADDW)          _mm256_maddubs_epi16 (VPMADDUBSW)          _mm256_mpsadbw_epu8 (VMPSADBW)          _mm256_mul_epi32 (VPMULDQ)          _mm256_mul_epu32 (VPMULUDQ)          _mm256_mulhi_epi16 (VPMULHW)          _mm256_mulhi_epu16 (VPMULHUW)          _mm256_mulhrs_epi16 (VPMULHRSW)          _mm256_mullo_epi16 (VPMULLW)          _mm256_mullo_epi32 (VPMULLD)          _mm256_sad_epu8 (VPSADBW)          _mm256_sign_epi16 (VPSIGNW)          _mm256_sign_epi32 (VPSIGND)          _mm256_sign_epi8 (VPSIGNB)          _mm256_sub_epi16 (VPSUBW)          _mm256_sub_epi32 (VPSUBD)          _mm256_sub_epi64 (VPSUBQ)          _mm256_sub_epi8 (VPSUBB)          _mm256_subs_epi16 (VPSUBSW)          _mm256_subs_epi8 (VPSUBSB)          _mm256_subs_epu16 (VPSUBUSW)          _mm256_subs_epu8 (VPSUBUSB)       arithmetic shift operations          Intrinsics for Arithmetic Shift Operations          _mm_srav_epi32 (VPSRAVD)          _mm256_sra_epi16 (VPSRAW)          _mm256_sra_epi32 (VPSRAD)          _mm256_srai_epi16 (VPSRAW)          _mm256_srai_epi32 (VPSRAD)          _mm256_srav_epi32 (VPSRAVD)       bit manipulation operations          Intrinsics for Operations to Manipulate Integer Data at Bit-Granularity          _bextr_u32 (BEXTR)          _bextr_u64 (BEXTR)          _blsi_u32 (BLSI)          _blsi_u64 (BLSI)          _blsmsk_u32 (BLSMSK)          _blsmsk_u64 (BLSMSK)          _blsr_u64 (BLSR)          _bslr_u32 (BLSR)          _lzcnt_u32 (LZCNT)             _bzhi_u32/64             _lzcnt_u32/64          _lzcnt_u64 (LZCNT)             _bzhi_u32/64             _lzcnt_u32/64          _pdep_u32 (PDEP)          _pdep_u64 (PDEP)          _pext_u32 (PEXT)          _pext_u64 (PEXT)          _tzcnt_u32 (TZCNT)          _tzcnt_u64 (TZCNT)       bitwise logical operations          Intrinsics for Bitwise Operations           _mm256_xor_si256 (VPXOR)          _mm256_and_si256 (VPAND)          _mm256_andnot_si256 (VPANDN)          _mm256_or_si256 (VPOR)       blend operations          Intrinsics for Blend Operations          _mm_blend_epi32          _mm256_blend_epi16 (VPBLENDW)          _mm256_blend_epi32 (VPBLENDD)          _mm256_blend_epi32 (VPBLENDVB)       broadcast operations          Intrinsics for Broadcast Operations           _mm_broadcastb_epi8 (VPBROADCASTB)          _mm_broadcastd_epi32 (VPBROADCASTD)          _mm_broadcastq_epi64 (VPBROADCASTQ)          _mm_broadcastsd_pd (VBROADCASTSD)          _mm_broadcastss_ps (VBROADCASTSS)          _mm_broadcastw_epi16 (VPBROADCASTW)          _mm256_broadcastb_epi8 (VPBROADCASTB)          _mm256_broadcastd_epi32 (VPBROADCASTD)          _mm256_broadcastq_epi64 (VPBROADCASTQ)          _mm256_broadcastsd_pd (VBROADCASTSD)          _mm256_broadcastsi128_si256 (VBROADCASTI128)          _mm256_broadcastsi128_si256 (VPERM2I128)          _mm256_broadcastss_ps (VBROADCASTSS)          _mm256_broadcastw_epi16 (VPBROADCASTW)       compare operations          Intrinsics for Compare Operations          _mm256_cmpeq_epi16 (VPCMPEQW)          _mm256_cmpeq_epi32 (VPCMPEQD)          _mm256_cmpeq_epi64 (VPCMPEQQ)          _mm256_cmpeq_epi8 (VPCMPEQB)          _mm256_cmpgt_epi16 (VPCMPGTW)          _mm256_cmpgt_epi32 (VPCMPGTD)          _mm256_cmpgt_epi64 (VPCMPGTQ)          _mm256_cmpgt_epi8 (VPCMPGTB)          _mm256_max_epi16 (VPMAXSW)          _mm256_max_epi32 (VPMAXSD)          _mm256_max_epi8 (VPMAXSB)          _mm256_max_epu16 (VPMAXUW)          _mm256_max_epu32 (VPMAXUD)          _mm256_max_epu8 (VPMAXUB)          _mm256_min_epi16 (VPMINSW)          _mm256_min_epi32 (VPMINSD)          _mm256_min_epi8 (VPMINSB)          _mm256_min_epu16 (VPMINUW)          _mm256_min_epu32 (VPMINUD)          _mm256_min_epu8 (VPMINUB)       fused multiply-add (FMA) operations          Intrinsics for Fused Multiply Add Operations          _mm_fmadd_pd (VFMADD###)          _mm_fmadd_ps (VFMADD###)          _mm_fmadd_sd (VFMADD###)          _mm_fmadd_ss (VFMADD###)          _mm_fmaddsub_pd (VFMADDSUB###)          _mm_fmaddsub_ps (VFMADDSUB###)          _mm_fmsub_pd (VFMSUB###)          _mm_fmsub_ps (VFMSUB###)          _mm_fmsub_sd (VFMSUB###)          _mm_fmsub_ss (VFMSUB###)          _mm_fmsubadd_pd (VFMSUBADD###)          _mm_fmsubadd_ps (VFMSUBADD###)          _mm_fnmadd_pd (VFNMADD###)          _mm_fnmadd_ps (VFNMADD###)          _mm_fnmadd_sd (VFNMADD###)          _mm_fnmadd_ss (VFNMADD###)          _mm_fnmsub_pd (VFNMSUB###)          _mm_fnmsub_ps (VFNMSUB###)          _mm_fnmsub_sd (VFNMSUB###)          _mm_fnmsub_ss (VFNMSUB###)          _mm256_fmadd_pd (VFMADD###)          _mm256_fmadd_ps (VFMADD###)          _mm256_fmadd_sd (VFMADD###)          _mm256_fmadd_ss (VFMADD###)          _mm256_fmaddsub_pd (VFMADDSUB###)          _mm256_fmaddsub_ps (VFMADDSUB###)          _mm256_fmsub_pd (VFMSUB###)          _mm256_fmsub_ps (VFMSUB###)          _mm256_fmsub_sd (VFMSUB###)          _mm256_fmsub_ss (VFMSUB###)          _mm256_fmsubadd_pd (VFMSUBADD###)          _mm256_fmsubadd_ps (VFMSUBADD###)          _mm256_fnmadd_pd (VFNMADD###)          _mm256_fnmadd_ps (VFNMADD###)          _mm256_fnmadd_sd (VFNMADD###)          _mm256_fnmadd_ss (VFNMADD###)          _mm256_fnmsub_pd (VFNMSUB###)          _mm256_fnmsub_ps (VFNMSUB###)          _mm256_fnmsub_sd (VFNMSUB###)          _mm256_fnmsub_ss (VFNMSUB###)       GATHER operations          Intrinsics for GATHER Operations          _mm_i32gather_epi32 (VPGATHERDD)          _mm_i32gather_epi64 (VPGATHERDQ)          _mm_i32gather_pd (VGATHERDPD)          _mm_i64gather_epi32 (VPGATHERQD)          _mm_i64gather_epi64 (VPGATHERQQ)          _mm_i64gather_pd (VGATHERQPD)          _mm_i64gather_ps (VGATHERQPS)          _mm_mask_i32gather_epi32 (VPGATHERDD)          _mm_mask_i32gather_epi64 (VPGATHERDQ)          _mm_mask_i32gather_ps (VGATHERDPS)             _mm_mask_i32gather_ps, _mm256_mask_i32gather_ps             _mm_i32gather_ps, _mm256_i32gather_ps          _mm_mask_i64gather_epi32 (VPGATHERQD)          _mm_mask_i64gather_epi64 (VPGATHERQQ)          _mm_mask_i64gather_pd (VGATHERQPD)          _mm_mask_i64gather_ps (VGATHERQPS)          _mm256_i32gather_epi32 (VPGATHERDD)          _mm256_i32gather_epi64 (VPGATHERDQ)          _mm256_i64gather_epi32 (VPGATHERQD)          _mm256_i64gather_epi64 (VPGATHERQQ)          _mm256_i64gather_pd (VGATHERQPD)          _mm256_i64gather_ps (VGATHERQPS)          _mm256_mask_i32gather_epi32 (VPGATHERDD)          _mm256_mask_i32gather_epi64 (VPGATHERDQ)          _mm256_mask_i32gather_pd (VGATHERDPD)             _mm_mask_i32gather_pd, _mm256_mask_i32gather_pd             _mm_i32gather_pd, _mm256_i32gather_pd          _mm256_mask_i32gather_ps (VGATHERDPS)             _mm_mask_i32gather_ps, _mm256_mask_i32gather_ps             _mm_i32gather_ps, _mm256_i32gather_ps          _mm256_mask_i64gather_epi32 (VPGATHERQD)          _mm256_mask_i64gather_epi64 (VPGATHERQQ)          _mm256_mask_i64gather_pd (VGATHERQPD)          _mm256_mask_i64gather_ps (VGATHERQPS)       insert and extract operations          Intrinsics for Insert/Extract Operations          _mm256_extracti128_si256 (VEXTRACTI128)          _mm256_inserti128_si256 (VINSERTI128)       load and store operations       logical shift operations          Intrinsics for Logical Shift Operations           _mm256_srl_epi16 (VPSRLW)           _mm256_srli_epi16 (VPSRLW)          _mm_sllv_epi16 (VPSLLVD)          _mm_sllv_epi32 (VPSLLVQ)          _mm_srlv_epi16 (VPSRLVD)          _mm_srlv_epi32 (VPSRLVQ)          _mm256_sll_epi16 (VPSLLW)          _mm256_sll_epi32 (VPSLLD)          _mm256_sll_epi64 (VPSLLQ)          _mm256_slli_epi16 (VPSLLW)          _mm256_slli_epi32 (VPSLLD)          _mm256_slli_epi64 (VPSLLQ)          _mm256_slli_si256 (VPSLLDQ)          _mm256_sllv_epi32 (VPSLLVD)          _mm256_sllv_epi64 (VPSLLVQ)          _mm256_srl_epi32 (VPSRLD)          _mm256_srl_epi64 (VPSRLQ)          _mm256_srli_epi32 (VPSRLD)          _mm256_srli_epi64 (VPSRLQ)          _mm256_srli_si256 (VPSRLDQ)          _mm256_srlv_epi32 (VPSRLVD)          _mm256_srlv_epi64 (VPSRLVQ)       masked load and store operations          _mm_maskload_epi32/64, _mm256_maskload_epi32/64          _mm_maskstore_epi32/64, _mm256_maskstore_epi32/64          _mm256_maskload_epi32 (VPMASKMOVD)          _mm256_maskload_epi64 (VPMASKMOVQ)          _mm256_maskstore_epi32 (VPMASKMOVD)          _mm256_maskstore_epi64 (VPMASKMOVQ)       miscellaneous operations          Intrinsics for Miscellaneous Operations          _mm256_alignr_epi8 (VPALIGNRB)          _mm256_movemask_epi8 (VPMOVMSKB)          _mm256_stream_load_si256 (VMOVNTDQA)       overview       pack and unpack operations          Intrinsics for Pack/Unpack Operations          _mm256_packs_epi16 (VPACKSSWB)          _mm256_packs_epi32 (VPACKSSDW)          _mm256_packus_epi16 (VPACKUSWB)          _mm256_packus_epi32 (VPACKUSDW)          _mm256_unpackhi_epi16 (VPUNPCKHWD)          _mm256_unpackhi_epi32 (VPUNPCKHDQ)          _mm256_unpackhi_epi64 (VPUNPCKHQDQ)          _mm256_unpackhi_epi8 (VPUNPCKHBW)          _mm256_unpacklo_epi16 (VPUNPCKLWD)          _mm256_unpacklo_epi32 (VPUNPCKLDQ)          _mm256_unpacklo_epi64 (VPUNPCKLQDQ)          _mm256_unpacklo_epi8 (VPUNPCKLBW)       packed move operations          Intrinsics for Packed Move with Extend Operations           _mm256_cvtepu8_epi16 (VPMOVZXBW)          _mm256_cvtepi16_epi32 (VPMOVSXWD)          _mm256_cvtepi16_epi64 (VPMOVSXWQ)          _mm256_cvtepi32_epi64 (VPMOVSXDQ)          _mm256_cvtepi8_epi16 (VPMOVSXBW)          _mm256_cvtepi8_epi32 (VPMOVSXBD)          _mm256_cvtepi8_epi64 (VPMOVSXBQ)          _mm256_cvtepu16_epi32 (VPMOVZXWD)          _mm256_cvtepu16_epi64 (VPMOVZXWQ)          _mm256_cvtepu32_epi64 (VPMOVZXDQ)          _mm256_cvtepu8_epi32 (VPMOVZXBD)          _mm256_cvtepu8_epi64 (VPMOVZXBQ)       permute operations          Intrinsics for Permute Operations          _mm256_permute4x64_epi64 (VPERMQ)          _mm256_permute4x64_pd (VPERMPD)          _mm256_permutevar8x32_epi32 (VPERM2I128)          _mm256_permutevar8x32_epi32 (VPERMD)          _mm256_permutevar8x32_epi32 (VPERMPS)       shuffle operations          Intrinsics for Shuffle Operations          _mm256_shuffle_epi32 (VPSHUFD)          _mm256_shuffle_epi8          _mm256_shuffle_epi8 (VPSHUFB)          _mm256_sufflehi_epi16 (VPSHUFHW)          _mm256_sufflelo_epi16 (VPSHUFLW)       Transactional Synchronization Extensions    Intel® SSE       Conversion Intrinsics       Arithmetic Intrinsics       Cacheability Support Intrinsics       Compare Intrinsics       Details about Intel® Streaming SIMD Extensions Intrinsics       Integer Intrinsics       Logical Intrinsics       Macro Function for Matrix Transposition       Macro Functions to Read and Write Control Registers       Macro Function for Shuffle Operations       Miscellaneous Intrinsics       Overview: Intel® Streaming SIMD Extensions       Writing Programs with Intel® Streaming SIMD Extensions Intrinsics       Set Intrinsics       Store Intrinsics       ***          Conversion Intrinsics          conversion operations          cvtpi16_ps          cvtpi32_ps          cvtpi32x2_ps          cvtpi8_ps          cvtps_pi16          cvtps_pi32          cvtps_pi8          cvtpu16_ps          cvtpu8_ps          cvtsi32_ss          cvtsi64_ss          cvtss_f32          cvtss_si32          cvtss_si64          cvttps_pi32          cvttss_si32          cvttss_si64       arithmetic operations          Arithmetic Intrinsics          add_ps          add_ss          div_ps          div_ss          max_ps          max_ss          min_ps          min_ss          mul_ps          mul_ss          rcp_ps          rcp_ss          rsqrt_ps          rsqrt_ss          sqrt_ps          sqrt_ss          sub_ps          sub_ss       cacheability support operations          Cacheability Support Intrinsics          prefetch          sfence          stream_pi          stream_ps       compare operations          Compare Intrinsics          cmpeq_ps          cmpeq_ss          cmpge_ps          cmpge_ss          cmpgt_ps          cmpgt_ss          cmple_ps          cmple_ss          cmplt_ps          cmplt_ss          cmpneq_ps          cmpneq_ss          cmpnge_ps          cmpnge_ss          cmpngt_ps          cmpngt_ss          cmpnle_ps          cmpnle_ss          cmpnlt_ps          cmpnlt_ss          cmpord_ps          cmpord_ss          cmpunord_ps          cmpunord_ss          comieq_ss          comige_ss          comigt_ss          comile_ss          comilt_ss          comineq_ss          ucomieq_ss          ucomige_ss          ucomigt_ss          ucomile_ss          ucomilt_ss          ucomineq_ss       data types       integer operations          Integer Intrinsics          avg_pu16          avg_pu8          extract_pi16          insert_pi16          maskmove_si641          max_pi16          max_pu8          min_pi16          min_pu8          movemask_pi8          mulhi_pu16          sad_pu8          shuffle_pi16       logical operations          Logical Intrinsics          and_ps          andnot_ps          or_ps          xor_ps       macros          Macro Function for Matrix Transposition          Macro Functions to Read and Write Control Registers          Macro Function for Shuffle Operations          matrix transposition          read control register          shuffle function          write control register       miscellaneous operations          Miscellaneous Intrinsics          move_ss          movehl_ps          movelh_ps          movemask_ps          shuffle_ps          unpackhi_ps          unpacklo_ps       overview       programming with Intel® SSE intrinsics       registers       set operations          Set Intrinsics          set_ps          set_ps1          set_ss          setr_ps          setzero_ps       store operations          Store Intrinsics          store_ps          store_ps1          store_ss          storeh_pi          storel_pi          storer_ps          storeu_ps    Intel® SSE2       Cacheability Support Intrinsics       Casting Support Intrinsics       Arithmetic Intrinsics       Compare Intrinsics       Conversion Intrinsics       Load Intrinsics       Logical Intrinsics       Set Intrinsics       Store Intrinsics       Arithmetic Intrinsics       Compare Intrinsics       Conversion Intrinsics       Load Intrinsics       Logical Intrinsics       Move Intrinsics       Set Intrinsics       Shift Intrinsics       Store Intrinsics       Miscellaneous Intrinsics       Overview: Intel® Streaming SIMD Extensions 2 (Intel® SSE2)       Pause Intrinsic       Macro Function for Shuffle       cacheability support operations          Cacheability Support Intrinsics          clflush          lfence          mfence          stream_pd          stream_si128          stream_si32       casting support          Casting Support Intrinsics          _mm_castpd_ps          _mm_castpd_si128          _mm_castps_pd          _mm_castps_si128          _mm_castsi128_pd          _mm_castsi128_ps       FP arithmetic operations          Arithmetic Intrinsics          add_pd          add_sd          div_pd          div_sd          max_pd          max_sd          min_pd          min_sd          mul_pd          mul_sd          sqrt_pd          sqrt_sd          sub_pd          sub_sd       FP compare operations          Compare Intrinsics          cmpeq_pd          cmpeq_sd          cmpge_pd          cmpge_sd          cmpgt_pd          cmpgt_sd          cmple_pd          cmple_sd          cmplt_pd          cmplt_sd          cmpneq_pd          cmpneq_sd          cmpnge_pd          cmpnge_sd          cmpngt_pd          cmpngt_sd          cmpnle_pd          cmpnle_sd          cmpnlt_pd          cmpnlt_sd          cmpord_pd          cmpord_sd          cmpunord_pd          cmpunord_sd          comieq_sd          comige_sd          comigt_sd          comile_sd          comilt_sd          comineq_sd          ucomieq_sd          ucomige_sd          ucomigt_sd          ucomile_sd          ucomilt_sd          ucomineq_sd       FP conversion operations          Conversion Intrinsics          cvtepi32_pd          cvtpd_epi32          cvtpd_pi32          cvtpd_ps          cvtpi32_pd          cvtps_pd          cvtsd_f64          cvtsd_si32          cvtsd_ss          cvtsi32_sd          cvtss_sd          cvttpd_epi32          cvttpd_pi32          cvttsd_si32       FP load operations          Load Intrinsics          load_pd          load_sd          load1_pd          loadh_pd          loadl_pd          loadr_pd          loadu_pd       FP logical operations          Logical Intrinsics          and_pd          andnot_pd          or_pd          xor_pd       FP set operations          Set Intrinsics          move_sd          set_pd          set_sd          set1_pd          setr_pd          setzero_pd       FP store operations          Store Intrinsics          store_pd          store_sd          store1_pd          storeh_pd          storel_pd          storer_pd          storeu_pd       integer arithmetic operations          Arithmetic Intrinsics          add_epi16          add_epi32          add_epi64          add_epi8          add_si64          adds_epi16          adds_epi8          adds_epu16          adds_epu8          avg_epu16          avg_epu8          madd_epi16          max_epi16          max_epu8          min_epi16          min_epu8          mul_epu32          mul_su32          mulhi_epi16          mulhi_epu16          mullo_epi16          sad_epu8          sub_epi16          sub_epi32          sub_epi64          sub_epi8          sub_si64          subs_epi16          subs_epi8          subs_epu16          subs_epu8       integer compare operations          Compare Intrinsics          cmpeq_epi16          cmpeq_epi32          cmpeq_epi8          cmpgt_epi16          cmpgt_epi32          cmpgt_epi8          cmplt_epi16          cmplt_epi32          cmplt_epi8       integer conversion operations          Conversion Intrinsics          cvtepi32_ps          cvtps_epi32          cvtsd_si64          cvtsi64_sd          cvttps_epi32          cvttsd_si64       integer load operations          Load Intrinsics          load_si128          loadl_epi64          loadu_si128       integer logical operations          Logical Intrinsics          and_si128          andnot_si128          or_si128          xor_si128       integer move operations          Move Intrinsics          cvtsi128_si32          cvtsi128_si64          cvtsi32_si128          cvtsi64_si128       integer set operations          Set Intrinsics          set_epi16          set_epi32          set_epi64          set_epi8          set1_epi16          set1_epi32          set1_epi64          set1_epi8          setr_epi16          setr_epi32          setr_epi64          setr_epi8          setzero_si128       integer shift operations          Shift Intrinsics          sll_epi16          sll_epi32          sll_epi64          slli_epi16          slli_epi32          slli_epi64          slli_si128          sra_epi16          sra_epi32          srai_epi16          srai_epi32          srl_epi16          srl_epi32          srl_epi64          srli_epi16          srli_epi32          srli_epi64          srli_si128       integer store operations          Store Intrinsics          maskmoveu_si128          store_si128          storel_epi64          storeu_si128       miscellaneous operations          Miscellaneous Intrinsics          extract_epi16          insert_epi16          move_epi64          movemask_epi8          movemask_pd          movepi64_pi64          movpi64_pi64          packs_epi16          packs_epi32          packus_epi16          shuffle_epi32          shuffle_pd          shufflehi_epi16          shufflelo_epi16          unpackhi_epi16          unpackhi_epi32          unpackhi_epi64          unpackhi_epi8          unpackhi_pd          unpacklo_epi16          unpacklo_epi32          unpacklo_epi64          unpacklo_epi8          unpacklo_pd       overview       pause intrinsic       shuffle macro    Intel® SSE3       Single-precision Floating-point Vector Intrinsics       Double-precision Floating-point Vector Intrinsics       Integer Vector Intrinsic       Macro Functions       Miscellaneous Intrinsics       Overview: Intel® Streaming SIMD Extensions 3 (Intel® SSE3)       float32 vector intrinsics          Single-precision Floating-point Vector Intrinsics          addsub_ps          hadd_ps          hsub_ps          movehdup_ps          moveldup_ps       float64 vector intrinsics          Double-precision Floating-point Vector Intrinsics          addsub_pd          hadd_pd          hsub_pd          loaddup_pd          movedup_pd       integer vector intrinsic          Integer Vector Intrinsic          lddqu_si128       macro functions       miscellaneous intrinsics       overview    Intel® SSE4       Application Targeted Accelerators Intrinsics       Cacheability Support Intrinsic       DWORD Multiply Intrinsics       Floating Point Rounding Intrinsics       Floating Point Dot Product Intrinsics       Overview: Intel® Streaming SIMD Extensions 4 (Intel® SSE4)       Packed Blending Intrinsics       Packed Compare for Equal Intrinsic       Packed Compare Intrinsics       Packed DWORD to Unsigned WORD Intrinsic       Packed Format Conversion Intrinsics       Packed Integer Min/Max Intrinsics       Register Insertion/Extraction Intrinsics       Test Intrinsics       application targeted accelerator intrinsics          Application Targeted Accelerators Intrinsics          _mm_crc32_u16          _mm_crc32_u32          _mm_crc32_u64          _mm_crc32_u8          _mm_popcnt_u64          _mm_popcnt_u32       cacheability support intrinsic          Cacheability Support Intrinsic          _mm_stream_load_si128          MOVNTDQA       DWORD multiply operations          DWORD Multiply Intrinsics          _m128i _mm_mul_epi32          _m128i _mm_mullo_epi32       floating-point rounding operations          Floating Point Rounding Intrinsics          _mm_ceil_pd          _mm_ceil_ps          _mm_ceil_sd          _mm_ceil_ss          _mm_floor_pd          _mm_floor_ps          _mm_floor_sd          _mm_floor_ss          _mm_round_pd          _mm_round_ps          _mm_round_sd          _mm_round_ss       FP dot product operations          Floating Point Dot Product Intrinsics          _mm_dp_pd          _mm_dp_ps       overview       packed blending operations          Packed Blending Intrinsics          _mm_blend_epi16          _mm_blend_pd          _mm_blend_ps          _mm_blendv_epi8          _mm_blendv_pd          _mm_blendv_ps       packed compare for equal intrinsic          _mm_cmpeq_epi64          PCMPEQQ       packed compare operations          Packed Compare Intrinsics          _cmpestra          _cmpestrc          _cmpestri          _cmpestrm          _cmpestro          _cmpestrs          _cmpestrz          _cmpistra          _cmpistrc          _cmpistri          _cmpistrm          _cmpistro          _cmpistrs          _cmpistrz          PCMPESTRA          PCMPESTRC          PCMPESTRI          PCMPESTRM          PCMPESTRO          PCMPESTRS          PCMPESTRZ          PCMPISTRA          PCMPISTRC          PCMPISTRI          PCMPISTRM          PCMPISTRO          PCMPISTRS          PCMPISTRZ       packed DWORD to unsigned WORD intrinsic          Packed DWORD to Unsigned WORD Intrinsic          _mm_packus_epi32          PACKUSDW       packed format conversion operations          Packed Format Conversion Intrinsics          _mm_cvtepi16_epi32          _mm_cvtepi16_epi64          _mm_cvtepi32_epi64          _mm_cvtepi8_epi16          _mm_cvtepi8_epi32          _mm_cvtepi8_epi64          _mm_cvtepu16_epi32          _mm_cvtepu16_epi64          _mm_cvtepu32_epi64          _mm_cvtepu8_epi16          _mm_cvtepu8_epi32          _mm_cvtepu8_epi64          PMOVSXBD          PMOVSXBQ          PMOVSXBW          PMOVSXDQ          PMOVSXWD          PMOVSXWQ          PMOVZXBD          PMOVZXBQ          PMOVZXBW          PMOVZXDQ          PMOVZXWD          PMOVZXWQ       packed integer min/max intrinsics          _mm_max_epi16          _mm_max_epi32          _mm_max_epi8          _mm_max_epu32          _mm_min_epi16          _mm_min_epi32          _mm_min_epi8          _mm_min_epu32          PMAXSB          PMAXSD          PMAXUD          PMAXUW          PMINSB          PMINSD          PMINUW       register insertion/extraction operations          Register Insertion/Extraction Intrinsics          _mm_extract_epi16          _mm_extract_epi32          _mm_extract_epi64          _mm_extract_epi8          _mm_extract_ps          _mm_insert_epi32          _mm_insert_epi64          _mm_insert_epi8          _mm_insert_ps          EXTRACTPS          INSERTPS          PEXTRB          PEXTRD          PEXTRQ          PEXTRW          PINSRB          PINSRD          PINSRQ       test operations          Test Intrinsics          _mm_testc_si128          _mm_testnzc_si128          _mm_testz_si128    Intel® Streaming SIMD Extensions       Arithmetic Intrinsics       arithmetic operations    Intel® Streaming SIMD Extensions 3       Single-precision Floating-point Vector Intrinsics       Miscellaneous Intrinsics       float32 vector intrinsics       miscellaneous intrinsics    memory allocation       Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly       Allocating and Freeing Aligned Memory Blocks    MMX™ Technology       MMX™ Technology Compare Intrinsics       Details about MMX™ Technology Intrinsics       The EMMS Instruction: Why You Need It       EMMS Usage Guidelines       MMX™ Technology General Support Intrinsics       MMX™ Technology Logical Intrinsics       Overview: MMX™ Technology Intrinsics       MMX™ Technology Packed Arithmetic Intrinsics       MMX™ Technology Set Intrinsics       MMX™ Technology Shift Intrinsics       compare operations          MMX™ Technology Compare Intrinsics          cmpeq_pi16          cmpeq_pi32          cmpeq_pi8          cmpgt_pi16          cmpgt_pi32          cmpgt_pi8       data types       EMMS instruction          The EMMS Instruction: Why You Need It          EMMS Usage Guidelines          about          using       general support operations          MMX™ Technology General Support Intrinsics          cvtm64_si64          cvtsi32_si64          cvtsi64_m64          cvtsi64_si32          empty          packs_pi16          packs_pi32          packs_pu16          unpackhi_pi16          unpackhi_pi32          unpackhi_pi8          unpacklo_pi16          unpacklo_pi32          unpacklo_pi8       logical operations          MMX™ Technology Logical Intrinsics          and_si64          andnot_si64          or_si64          xor_si64       overview       packed arithmetic operations          MMX™ Technology Packed Arithmetic Intrinsics          add_pi16          add_pi32          add_pi8          adds_pi16          adds_pi8          adds_pu16          adds_pu8          madd_pi16          mulhi_pi16          mullo_pi16          sub_pi16          sub_pi32          sub_pi8          subs_pi16          subs_pi8          subs_pu16          subs_pu8       registers       set operations          MMX™ Technology Set Intrinsics          set_pi16          set_pi32          set_pi8          set1_pi16          set1_pi32          set1_pi8          setr_pi16          setr_pi32          setr_pi8          setzero_si64       shift operations          MMX™ Technology Shift Intrinsics          sll_pi16          sll_pi32          slli_pi16          slli_pi32          slli_pi64          sra_pi16          sra_pi32          srai_pi16          srai_pi32          srl_pi16          srl_pi32          srl_pi64          srli_pi16          srli_pi32          srli_pi64    naming and syntax    registers    SSSE3       Absolute Value Intrinsics       Addition Intrinsics       Concatenate Intrinsics       Multiplication Intrinsics       Negation Intrinsics       Overview: Supplemental Streaming SIMD Extensions 3 (SSSE3)       Shuffle Intrinsics       Subtraction Intrinsics       absolute value operations          Absolute Value Intrinsics          _mm_abs_epi16          _mm_abs_epi32          _mm_abs_epi8          _mm_abs_pi16          _mm_abs_pi32          _mm_abs_pi8       addition operations          Addition Intrinsics          _mm_hadd_epi16          _mm_hadd_epi32          _mm_hadd_pi16          _mm_hadd_pi32          _mm_hadds_epi16          _mm_hadds_pi16       concatenate operations          Concatenate Intrinsics          _mm_alignr_epi8          _mm_alignr_pi8       multiplication operations          Multiplication Intrinsics          _mm_maddubs_epi16          _mm_maddubs_pi16          _mm_mulhrs_epi16          _mm_mulhrs_pi16       negation operations       overview       shuffle operations       subtraction operations    SVML       _mm_cexp_ps, _mm256_cexp_ps       _mm_clog_ps, _mm256_clog_ps       _mm_csqrt_ps, _mm256_csqrt_ps       _mm_cdfnorminv_pd, _mm256_cdfnorminv_pd       _mm_cdfnorminv_ps, _mm256_cdfnorminv_ps       _mm_erf_pd, _mm256_erf_pd       _mm_erf_ps, _mm256_erf_ps       _mm_erfc_pd, _mm256_erfc_pd       _mm_erfc_ps, _mm256_erfc_ps       _mm_erfinv_pd, _mm256_erfinv_pd       _mm_erfinv_ps, _mm256_erfinv_ps       _mm_exp2_pd, _mm256_exp2_pd       _mm_exp2_ps, _mm256_exp2_ps       _mm_hypot_ps, _mm256_hypot_ps       _mm_exp_pd, _mm256_exp_pd       _mm_exp_ps, _mm256_exp_ps       _mm_exp10_pd, _mm256_exp10_pd       _mm_exp10_ps, _mm256_exp10_ps       _mm_expm1_pd, _mm256_expm1_pd       _mm_expm1_ps, _mm256_expm1_ps       _mm_hypot_pd, _mm256_hypot_pd       _mm_pow_pd, _mm256_pow_pd       _mm_pow_ps, _mm256_pow_ps       _mm_log_pd, _mm256_log_pd       _mm_log_ps, _mm256_log_ps       _mm_log10_pd, _mm256_log10_pd       _mm_log10_ps, _mm256_log10_ps       _mm_log1p_pd, _mm256_log1p_pd       _mm_log1p_ps, _mm256_log1p_ps       _mm_log2_pd, _mm256_log2_pd       _mm_log2_ps, _mm256_log2_ps       _mm_logb_pd, _mm256_logb_pd       _mm_logb_ps, _mm256_logb_ps       Overview: Intrinsics for Short Vector Math Library (SVML) Functions       _mm_sqrt_ps, _mm256_sqrt_ps       _mm_cbrt_pd, _mm256_cbrt_pd       _mm_cbrt_ps, _mm256_cbrt_ps       _mm_invcbrt_pd, _mm256_invcbrt_pd       _mm_invcbrt_ps, _mm256_invcbrt_ps       _mm_invsqrt_pd, _mm256_invsqrt_pd       _mm_invsqrt_ps, _mm256_invsqrt_ps       _mm_sqrt_pd, _mm256_sqrt_pd       _mm_sinh_ps, _mm256_sinh_ps       _mm_acos_pd, _mm256_acos_pd       _mm_acos_ps, _mm256_acos_ps       _mm_acosh_pd, _mm256_acosh_pd       _mm_acosh_ps, _mm256_acosh_ps       _mm_asin_pd, _mm256_asin_pd       _mm_asin_ps, _mm256_asin_ps       _mm_asinh_pd, _mm256_asinh_pd       _mm_asinh_ps, _mm256_asinh_ps       _mm_atan_pd, _mm256_atan_pd       _mm_atan_ps, _mm256_atan_ps       _mm_atan2_pd, _mm256_atan2_pd       _mm_atan2_ps, _mm256_atan2_ps       _mm_atanh_pd, _mm256_atanh_pd       _mm_atanh_ps, _mm256_atanh_ps       _mm_cos_pd, _mm256_cos_pd       _mm_cos_ps, _mm256_cos_ps       _mm_cosd_pd, _mm256_cosd_pd       _mm_cosd_ps, _mm256_cosd_ps       _mm_cosh_pd, _mm256_cosh_pd       _mm_cosh_ps, _mm256_cosh_ps       _mm_sin_pd, _mm256_sin_pd       _mm_sin_ps, _mm256_sin_ps       _mm_sincos_pd, _mm256_sincos_pd       _mm_sincos_ps, _mm256_sincos_ps       _mm_sind_pd, _mm256_sind_pd       _mm_sind_ps, _mm256_sind_ps       _mm_sinh_pd, _mm256_sinh_pd       _mm_tan_pd, _mm256_tan_pd       _mm_tan_ps, _mm256_tan_ps       _mm_tand_pd, _mm256_tand_pd       _mm_tand_ps, _mm256_tand_ps       _mm_tanh_pd, _mm256_tanh_pd       _mm_tanh_ps, _mm256_tanh_ps       complex functions          _mm_cexp_ps, _mm256_cexp_ps          _mm_clog_ps, _mm256_clog_ps          _mm_csqrt_ps, _mm256_csqrt_ps          _mm_cexp_ps, _mm256_cexp_ps          _mm_clog_ps, _mm256_clog_ps          _mm_csqrt_ps, _mm256_csqrt_ps       error functions          _mm_cdfnorminv_pd, _mm256_cdfnorminv_pd          _mm_cdfnorminv_ps, _mm256_cdfnorminv_ps          _mm_erf_pd, _mm256_erf_pd          _mm_erf_ps, _mm256_erf_ps          _mm_erfc_pd, _mm256_erfc_pd          _mm_erfc_ps, _mm256_erfc_ps          _mm_erfinv_pd, _mm256_erfinv_pd          _mm_erfinv_ps, _mm256_erfinv_ps          _mm_cdfnorminv_pd, _mm256_cdfnorminv_pd          _mm_cdfnorminv_ps, _mm256_cdfnorminv_ps          _mm_erf_pd, _mm256_erf_pd          _mm_erf_ps, _mm256_erf_ps          _mm_erfc_pd, _mm256_erfc_pd          _mm_erfc_ps, _mm256_erfc_ps          _mm_erfinv_pd, _mm256_erfinv_pd          _mm_erfinv_ps, _mm256_erfinv_ps       exponential functions          _mm_exp2_pd, _mm256_exp2_pd          _mm_exp2_ps, _mm256_exp2_ps          _mm_hypot_ps, _mm256_hypot_ps          _mm_exp_pd, _mm256_exp_pd          _mm_exp_ps, _mm256_exp_ps          _mm_exp10_pd, _mm256_exp10_pd          _mm_exp10_ps, _mm256_exp10_ps          _mm_expm1_pd, _mm256_expm1_pd          _mm_expm1_ps, _mm256_expm1_ps          _mm_hypot_pd, _mm256_hypot_pd          _mm_pow_pd, _mm256_pow_pd          _mm_pow_ps, _mm256_pow_ps          _mm_exp2_pd, _mm256_exp2_pd          _mm_exp2_ps, _mm256_exp2_ps          _mm_hypot_ps, _mm256_hypot_ps          _mm_exp_pd, _mm256_exp_pd          _mm_exp_ps, _mm256_exp_ps          _mm_exp10_pd, _mm256_exp10_pd          _mm_exp10_ps, _mm256_exp10_ps          _mm_expm1_pd, _mm256_expm1_pd          _mm_expm1_ps, _mm256_expm1_ps          _mm_hypot_pd, _mm256_hypot_pd          _mm_pow_pd, _mm256_pow_pd          _mm_pow_ps, _mm256_pow_ps       logarithmic functions          _mm_log_pd, _mm256_log_pd          _mm_log_ps, _mm256_log_ps          _mm_log10_pd, _mm256_log10_pd          _mm_log10_ps, _mm256_log10_ps          _mm_log1p_pd, _mm256_log1p_pd          _mm_log1p_ps, _mm256_log1p_ps          _mm_log2_pd, _mm256_log2_pd          _mm_log2_ps, _mm256_log2_ps          _mm_logb_pd, _mm256_logb_pd          _mm_logb_ps, _mm256_logb_ps          _mm_log_pd, _mm256_log_pd          _mm_log_ps, _mm256_log_ps          _mm_log10_pd, _mm256_log10_pd          _mm_log10_ps, _mm256_log10_ps          _mm_log1p_pd, _mm256_log1p_pd          _mm_log1p_ps, _mm256_log1p_ps          _mm_log2_pd, _mm256_log2_pd          _mm_log2_ps, _mm256_log2_ps          _mm_logb_pd, _mm256_logb_pd          _mm_logb_ps, _mm256_logb_ps       overview       square and cube root functions          _mm_sqrt_ps, _mm256_sqrt_ps          _mm_cbrt_pd, _mm256_cbrt_pd          _mm_cbrt_ps, _mm256_cbrt_ps          _mm_invcbrt_pd, _mm256_invcbrt_pd          _mm_invcbrt_ps, _mm256_invcbrt_ps          _mm_invsqrt_pd, _mm256_invsqrt_pd          _mm_invsqrt_ps, _mm256_invsqrt_ps          _mm_sqrt_pd, _mm256_sqrt_pd          _mm_sqrt_ps, _mm256_sqrt_ps          _mm_cbrt_pd, _mm256_cbrt_pd          _mm_cbrt_ps, _mm256_cbrt_ps          _mm_invcbrt_pd, _mm256_invcbrt_pd          _mm_invcbrt_ps, _mm256_invcbrt_ps          _mm_invsqrt_pd, _mm256_invsqrt_pd          _mm_invsqrt_ps, _mm256_invsqrt_ps          _mm_sinh_pd, _mm256_sinh_pd       trigonometric functions          _mm_sinh_ps, _mm256_sinh_ps          _mm_acos_pd, _mm256_acos_pd          _mm_acos_ps, _mm256_acos_ps          _mm_acosh_pd, _mm256_acosh_pd          _mm_acosh_ps, _mm256_acosh_ps          _mm_asin_pd, _mm256_asin_pd          _mm_asin_ps, _mm256_asin_ps          _mm_asinh_pd, _mm256_asinh_pd          _mm_asinh_ps, _mm256_asinh_ps          _mm_atan_pd, _mm256_atan_pd          _mm_atan_ps, _mm256_atan_ps          _mm_atan2_pd, _mm256_atan2_pd          _mm_atan2_ps, _mm256_atan2_ps          _mm_atanh_pd, _mm256_atanh_pd          _mm_atanh_ps, _mm256_atanh_ps          _mm_cos_pd, _mm256_cos_pd          _mm_cos_ps, _mm256_cos_ps          _mm_cosd_pd, _mm256_cosd_pd          _mm_cosd_ps, _mm256_cosd_ps          _mm_cosh_pd, _mm256_cosh_pd          _mm_cosh_ps, _mm256_cosh_ps          _mm_sin_pd, _mm256_sin_pd          _mm_sin_ps, _mm256_sin_ps          _mm_sincos_pd, _mm256_sincos_pd          _mm_sincos_ps, _mm256_sincos_ps          _mm_sind_pd, _mm256_sind_pd          _mm_sind_ps, _mm256_sind_ps          _mm_sinh_pd, _mm256_sinh_pd          _mm_tan_pd, _mm256_tan_pd          _mm_tan_ps, _mm256_tan_ps          _mm_tand_pd, _mm256_tand_pd          _mm_tand_ps, _mm256_tand_ps          _mm_tanh_pd, _mm256_tanh_pd          _mm_tanh_ps, _mm256_tanh_ps          _mm_sinh_ps, _mm256_sinh_ps          _mm_acos_pd, _mm256_acos_pd          _mm_acos_ps, _mm256_acos_ps          _mm_acosh_pd, _mm256_acosh_pd          _mm_acosh_ps, _mm256_acosh_ps          _mm_asin_pd, _mm256_asin_pd          _mm_asin_ps, _mm256_asin_ps          _mm_asinh_pd, _mm256_asinh_pd          _mm_asinh_ps, _mm256_asinh_ps          _mm_atan_pd, _mm256_atan_pd          _mm_atan_ps, _mm256_atan_ps          _mm_atan2_pd, _mm256_atan2_pd          _mm_atan2_ps, _mm256_atan2_ps          _mm_atanh_pd, _mm256_atanh_pd          _mm_atanh_ps, _mm256_atanh_ps          _mm_cos_pd, _mm256_cos_pd          _mm_cos_ps, _mm256_cos_ps          _mm_cosd_pd, _mm256_cosd_pd          _mm_cosd_ps, _mm256_cosd_ps          _mm_cosh_pd, _mm256_cosh_pd          _mm_cosh_ps, _mm256_cosh_ps          _mm_sin_pd, _mm256_sin_pd          _mm_sin_ps, _mm256_sin_ps          _mm_sincos_pd, _mm256_sincos_pd          _mm_sincos_ps, _mm256_sincos_ps          _mm_sind_pd, _mm256_sind_pd          _mm_sind_ps, _mm256_sind_ps          _mm_sinh_pd, _mm256_sinh_pd          _mm_tan_pd, _mm256_tan_pd          _mm_tan_ps, _mm256_tan_ps          _mm_tand_pd, _mm256_tand_pd          _mm_tand_ps, _mm256_tand_ps          _mm_tanh_pd, _mm256_tanh_pd          _mm_tanh_ps, _mm256_tanh_ps intrinsics    Load Intrinsics    Intrinsics to Read and Write Registers    Overview: Reduction Intrinsics    References    Intel® SSE       Load Intrinsics       Intrinsics to Read and Write Registers       load operations          Load Intrinsics          load_ps          load_ps1          load_ss          loadh_pi          loadl_pi          loadr_ps(          loadu_ps       read/write register intrinsics          Intrinsics to Read and Write Registers          getcsr          setcsr    Intel® Streaming SIMD Extensions       Intrinsics to Read and Write Registers       register intrinsics    reduction, overview    references IPO    ipo-jobs, Qipo-jobs    option specifying jobs during the link phase of IR IVDEP    High-Level Optimizations (HLO) Overview    effect when tuning applications jmpbuf jump jump tables    opt-jump-tables, Qopt-jump-tables    option enabling generation of keyword    _Cilk_offload    _Cilk_shared    _Cilk_offload    _Cilk_offload_to    _Cilk_shared KMP_AFFINITY    Thread Affinity Interface (Linux* and Windows*)    modifier    offset    permute    type KMP_LIBRARY KMP_STACKSIZE environment variable KMP_TOPOLOGY_METHOD KMP_TOPOLOGY_METHOD environment variable Lambda expressions Lambda Expressions    Details on Using Lambda Expressions in C++    Using Lambda Expressions with Intel® Threading Building Blocks    Lambda Function Object    Understanding Lambda-Capture    details on using in C++    Example with Intel® TBB    function object    lambda-capture language extensions    gcc Compatibility    g++*    gcc* LD_LIBRARY_PATH libgcc library    shared-libgcc    static-libgcc    option linking dynamically    option linking statically libraries    Intel Extension Routines to OpenMP*    OpenMP* Run-time Library Routines    Bdynamic    Bstatic    static    nodefaultlibs    print-multi-lib    Redistributing Libraries When Deploying Applications    OpenMP* run-time routines       Intel Extension Routines to OpenMP*       OpenMP* Run-time Library Routines    option enabling dynamic linking of    option enabling static linking of    option preventing linking with shared    option preventing use of standard    option printing location of system    redistributing libraries    Creating Libraries    Managing Libraries    Using Intel Shared Libraries    -c compiler option    -fPIC compiler option    -shared compiler option    creating your own    LD_LIBRARY_PATH    managing    shared       Creating Libraries       Using Intel Shared Libraries    static libraries, creating offload libraries, using in offloaded code library    L    l    option searching in specified directory for    option to search for Library extensions    Introduction    valarray implementation library functions    Inline Function Expansion    Intel extension    OpenMP* run-time routines library math functions    fmath-errno    option testing errno after calls to linker    Xlinker    link    option passing linker option to    option passing options to linking    Compilation Phases    option preventing use of startup files and libraries when    option preventing use of startup files when    option suppressing linking debug information linking options linking tools    Linking Tools and Options    xild       IPO-Related Performance Issues       Interprocedural Optimization (IPO) Overview       Creating a Library from IPO Objects    xilibtool    xilink       IPO-Related Performance Issues       Interprocedural Optimization (IPO) Overview linking tools IR linking with IPO Linux* compiler options    Specifying Include Files    Specifying Alternate Tools and Paths    Specifying Assembly Files    -I    -Qlocation    -Qoption    -S    -X Linux* compiler options    Specifying Object Files    -c    -o Linux* OS    Porting Linux* OS or OS X* Code to Windows* OS    porting from lock routines log file from offloaded code longjmp loop blocking factor    opt-block-factor, Qopt-block-factor    option specifying loop unrolling    Programming Guidelines for Vectorization    using the HLO optimizer loops    Loop Constructs    constructs    dependencies    distribution    interchange    option performing run-time checks for    option specifying blocking factor for    option specifying maximum times to unroll    option using aggressive unrolling for    parallelization       Programming with Auto-parallelization       Vectorization and Loops    transformations    vectorization macro names    D    option associating with an optional value macros    Equivalent Macros    Predefined Macros for Intel® MIC Architecture    ISO Standard Predefined Macros    Additional Predefined Macros    Predefined Macros for Interoperability main cover     Intel® C++ Compiler XE 13.1 User and Reference Guide    Legal Information main thread    Qpar-adjust-stack    option adjusting the stack size for maintainability    Avoiding Mixed Data Type Arithmetic Expressions    allocation makefiles    Modifying Your makefile    modifying makefiles, using manual processor dispatch Math Library    C99 Macros    Overview: Intel Math Library    Function List    Using Intel Math Library    C99 macros    for Linux* OS    function list    using on Linux* OS Math library    Trigonometric Functions    Trigonometric Functions       Trigonometric Functions       acos library function       acosd library function       asin library function       asind library function       atan library function       atan2 library function       atand library function       atand2 library function       cos library function       cosd library function       cot library function       cotd library function       sin library function       sincos library function       sincosd library function       sind library function       tan library function       tand library function Math library    Complex Functions    Exponential Functions    Hyperbolic Functions    Miscellaneous Functions    Nearest Integer Functions    Remainder Functions    Special Functions    Complex Functions       Complex Functions       cabs library function       cacos library function       cacosh library function       carg library function       casin library function       casinh library function       catan library function       catanh library function       ccos library function       ccosh library function       cexp library function       cexp10 library function       cimag library function       cis library function       clog library function       clog2 library function       conj library function       cpow library function       cproj library function       creal library function       csin library function       csinh library function       csqrt library function       ctan library function       ctanh library function    Exponential Functions       Exponential Functions       cbrt library function       exp library function       exp10 library function       exp2 library function       expm1 library function       frexp library function       hypot library function       ilogb library function       ldexp library function       log library function       log10 library function       log1p library function       log2 library function       logb library function       pow library function       scalb library function       scalbn library function       sqrt library function    Hyperbolic Functions       Hyperbolic Functions       acosh library function       asinh library function       atanh library function       cosh library function       sinh library function       sinhcosh library function       tanh library function    Miscellaneous Functions       Miscellaneous Functions       copysign library function       fabs library function       fdim library function       finite library function       fma library function       fmax library function       fmin library function       Miscellaneous Functions       nextafter library function    Nearest Integer Functions       Nearest Integer Functions       ceil library function       floor library function       llrint library function       llround library function       lrint library function       lround library function       modf library function       nearbyint library function       rint library function       round library function       trunc library function    Remainder Functions       Remainder Functions       fmod library function       remainder library function       remquo library function    Special Functions       Special Functions       annuity library function       compound library function       erf library function       erfc library function       gamma library function       gamma_r library function       j0 library function       j1 library function       jn library function       lgamma library function       lgamma_r library function       tgamma library function       y0 library function       y1 library function       yn library function math library functions    fimf-domain-exclusion, Qimf-domain-exclusion    fimf-arch-consistency, Qimf-arch-consistency    fimf-precision, Qimf-precision    option indicating domain for input arguments    option producing consistent results    option specifying a level of accuracy for matmul library call    opt-matmul, Qopt-matmul    option replacing matrix multiplication loop nests with matrix multiplication loop nests    opt-matmul, Qopt-matmul    option identifying and replacing measuring time and data transferred in offload regions memory layout transformations    opt-mem-layout-trans, Qopt-mem-layout-trans    option controlling level of memory loads    global-hoist, Qglobal-hoist    option enabling optimizations to move memory management    Managing Memory Allocation for Pointer Variables    alloc_if    free_if    pointer variables memory model    mcmodel    option specifying large    option specifying small or medium    option to use specific memory, allocating for parts of arrays memory, shared Microsoft Windows*    Porting Microsoft Windows* OS Code to Linux* OS or OS X*    porting from Microsoft* Visual C++    Qvc    option specifying compatibility with Microsoft* Visual Studio    Qvc    option specifying compatibility with mixing vectorizable types in a loop mock object files MOVBE instructions    minstruction, Qinstruction    option generating multi-version compiler support multiple coprocessors    Calling Functions on the CPU to Modify the Coprocessor's Execution Environment    declaring target number    declaring target type multiple processes    multiple-processes, MP    option creating multithreaded programs multithreading    Programming with Auto-parallelization    OpenMP* Support Libraries MXCSR register native Intel® MIC Architecture applications    About Building Native Intel® MIC Architecture Applications    about building nofusion normalized floating-point number Not-a-Number (NaN) object file    ipo-separate, Qipo-separate    bigobj    option generating one per source file    option increasing number of sections in object files    Specifying Object Files    specifying offload offload compilation    Displaying Options Passed to Offload Compilation    watch    offload-option    list of options passed to    option listing all options passed to    option passing additional options to    passing additional options to offload regions, measuring time and data transferred in offload_attribute pragma offload_transfer    pragma offload_wait    pragma offloading code omp atomic OMP directives    OpenMP* Examples    advanced issues    compatibility libraries       OpenMP* Source Compatibility and Interoperability with Other Compilers       OpenMP* Support Libraries    compatibility with other compilers    debugging    directives    environment variables    guidelines for using libraries    KMP_AFFINITY    legacy libraries       OpenMP* Source Compatibility and Interoperability with Other Compilers       OpenMP* Support Libraries    library file names    object-level interoperability    omp.h    parallel processing thread model    performance    run-time library routines    source compatibility    support libraries OMP pragmas    Worksharing Using OpenMP*    load balancing omp task omp taskwait omp taskyield Open Source tools OpenMP    Calling Functions on the CPU to Modify the Coprocessor's Execution Environment    coprocessor functions OpenMP directives    Using OpenMP*    syntax OpenMP*    openmp-report, Qopenmp-report    openmp, Qopenmp    openmp-stubs, Qopenmp-stubs    openmp-threadprivate, Qopenmp-threadprivate    Linking Debug Information    option controlling diagnostics    option enabling    option enabling programs in sequential mode    option specifying threadprivate    problems debugging with IDB OpenMP* affinity, specifying OpenMP* Fortran directives    OpenMP* Directives and Clauses Summary    clauses for    examples of    Intel extensions for OpenMP* Libraries    Using the OpenMP* Libraries    using OpenMP* run-time library    openmp-link    openmp-lib, Qopenmp-lib    option controlling which is linked to    option specifying OpenMP*, defaults optimization    Other Considerations    option enabling prefetch insertion    option generating single assembly file from multiple files    option generating single object file from multiple files    option specifying code optimization report    opt-report-help, Qopt-report-help    opt-report-routine, Qopt-report-routine    opt-report, Qopt-report    opt-report-file, Qopt-report-file    opt-report-phase, Qopt-report-phase    option displaying phases for    option generating for routines with specified text    option generating to stderr    option specifying name for    option specifying phase to use for optimization_parameter optimizations    High-Level Optimizations (HLO) Overview    Od    Ot    Os    guide-opts, Qguide-opts    Profile-Guided Optimizations Overview    high-level language    option disabling all    option enabling all speed    option enabling many speed    option generating recommendations to improve    overview of    profile-guided option mapping tool ORDERED    OpenMP* Directives and Clauses Summary    overview of OpenMP* directives and clauses output files    o    option specifying name for overflow    OpenMP* Run-time Library Routines    call to a runtime library routine PARALLEL DO    OpenMP* Directives and Clauses Summary    summary of OpenMP* directives and clauses PARALLEL OpenMP* directive parallel pragma    Enabling Further Loop Parallelization for Multicore Platforms    lastprivate clause    private clause parallel processing    Parallel Processing Model    thread model parallel region    par-num-threads, Qpar-num-threads    option specifying number of threads to use in parallel regions PARALLEL SECTIONS    OpenMP* Directives and Clauses Summary    summary of OpenMP* directives parallelism    Guided Auto Parallelism Overview    OpenMP* Run-time Library Routines    C/C++ Extensions for Array Notations Overview    Auto-Parallelization Overview parallelization    Using Guided Auto Parallelism    Guided Auto Parallelism Overview    Programming with Auto-parallelization    C/C++ Extensions for Array Notations Overview    Auto-Parallelization Overview    C/C++ Extensions for Array Notations performance performance issues with IPO PGO PGO API    Dumping Profile Information    Dumping and Resetting Profile Information    Resetting the Dynamic Profile Counters    Resetting Profile Information    Interval Profile Dumping    API Support Overview    _PGOPTI_Prof_Dump_All    _PGOPTI_Prof_Dump_And_Reset    _PGOPTI_Prof_Reset    _PGOPTI_Prof_Reset_ALL    _PGOPTI_Set_Interval_Prof_Dump    enable PGO tools    PGO Tools Overview    code coverage tool    profmerge    proforder    test prioritization tool pgopti.spi file pgouser.h header file pointer aliasing    opt-multi-version-aggressive, Qopt-multi-version-aggressive    option using aggressive multi-versioning check for pointer checker    Checking Arrays    Checking Bounds    Checking Custom Memory Allocators    Checking for Dangling Pointers    Checking Multi-Threaded Code    Checking Run-Time Library Functions    Finding and Reporting Out-of-Bounds Errors    How the Compiler Defines Bounds Information for Pointers    Pointer Checker Overview    Passing and Returning Bounds    Storing Bounds Information    Working with Enabled and Non-Enabled Modules    Writing a Wrapper    checking arrays    checking bounds    checking custom memory allocator    checking for dangling pointers    checking multi-threaded code    checking run-time library functions    finding and reporting errors    how bounds are defined    overview    passing and returning bounds    storing bounds information    working with enabled and non-enabled modules    wrappers       Checking Run-Time Library Functions       Writing a Wrapper    wrapping run-time library functions pointer checker    Pointer Checker Feature Summary    feature summary porting    Porting from GNU gcc* to Microsoft Visual C++*    Porting Linux* OS or OS X* Code to Windows* OS    Porting Microsoft Windows* OS Code to Linux* OS or OS X*    from GNU gcc* to Microsoft Visual C++*    from Linux* OS and OS X* to Windows* OS    from Microsoft Windows* to Linux* OS and OS X* porting applications    Porting from GNU gcc* to Microsoft Visual C++*    Porting Linux* OS or OS X* Code to Windows* OS    Porting Microsoft Windows* OS Code to Linux* OS or OS X*    Overview: Porting Applications position-independent code    fpie    fpic    option generating       fpie       fpic position-independent executable    pie    option producing position-independent external references    mdynamic-no-pic    option generating code with pragma    offload_attribute    offload_transfer    offload_wait    offload_attribute    offload_transfer    offload_wait pragma alloc_section pragma cilk grainsize pragma distribute_point pragma forceinline pragma inline pragma intel_omp_task pragma intel_omp_taskq pragma ivdep pragma loop_count pragma noinline pragma noparallel pragma noprefetch pragma nounroll pragma nounroll_and_jam pragma novector pragma offload pragma optimization_level pragma optimize pragma parallel pragma prefetch pragma simd    simd    User-mandated or SIMD Vectorization pragma unroll pragma unroll_and_jam pragma unused pragma vector    vector    aligned    always    assert    nontemporal    temporal    unaligned pragmas    help-pragma, Qhelp-pragma    option displaying Pragmas    Overview: Intel® C++ Compiler Pragmas    overview Pragmas    Intel-Supported Pragmas    Intel-supported Pragmas: Intel-specific predefined macros    ISO Standard Predefined Macros    Additional Predefined Macros    Predefined Macros for Interoperability preempting functions prefetch insertion    opt-prefetch, Qopt-prefetch    option enabling preprocessor variables    Predefined Macros for Intel® MIC Architecture    Writing Code that Should Not Be Built for CPU-Only Execution    Writing Target-Specific Code Using a Pragma prioritizing application tests PRIVATE    OpenMP* Directives and Clauses Summary    summary of data scope attribute clauses private variables processor    mtune    option optimizing for specific processor features    x, Qx    option telling which to target profile data records    prof-src-dir, Qprof-src-dir    prof-src-root-cwd, Qprof-src-root-cwd    prof-src-root, Qprof-src-root    option affecting search for    option letting you use relative paths when searching for       prof-src-root-cwd, Qprof-src-root-cwd       prof-src-root, Qprof-src-root profile-guided optimization    Profile-Guided Optimizations Overview    API support    data ordering optimization    dumping profile information    example of    function grouping optimization    function order lists optimization    function ordering optimization    funtion/loop execution time    interval profile dumping    overview    phases    resetting dynamic profile counters       Resetting the Dynamic Profile Counters       Resetting Profile Information    resetting profile information    support    usage model profile-optimized code    API Support Overview    dumping       Interval Profile Dumping       Dumping Profile Information    generating information    resetting dynamic counters for       Resetting the Dynamic Profile Counters       Resetting Profile Information profiling    prof-use, Qprof-use    prof-gen, Qprof-gen    prof-dir, Qprof-dir    prof-file, Qprof-file    option enabling use of information from    option instrumenting a program for    option specifying directory for output files    option specifying name for summary profiling information    prof-func-order, Qprof-func-order    prof-data-order, Qprof-data-order    option enabling function ordering    option using to order static data items profmerge program loops    Using Guided Auto Parallelism    Guided Auto Parallelism Overview    Auto-Parallelization Overview    parallel processing model programs    fast    falias    option maximizing speed in    option specifying aliasing should be assumed in redistributable package redistributing libraries REDUCTION    OpenMP* Directives and Clauses Summary    summary of data scope attribute clauses references to global function symbols    Bsymbolic-functions    option binding to shared library definitions references to global symbols    Bsymbolic    option binding to shared library definitions register allocator    opt-ra-region-strategy, Qopt-ra-region-strategy    option selecting method for partitioning relative error    fimf-accuracy-bits, Qimf-accuracy-bits    fimf-max-error, Qimf-max-error    option defining for math library function results    option defining maximum for math library function results remarks    Werror-all    option changing to errors removed compiler options report generation    Resetting the Dynamic Profile Counters    Resetting Profile Information    Intel Extension Routines to OpenMP*    OpenMP* Run-time Library Routines    Dumping and Resetting Profile Information    Requesting Compiler Reports with the xi* Tools    dynamic profile counters       Resetting the Dynamic Profile Counters       Resetting Profile Information    Intel extension    OpenMP* run-time    profile information    timing    using xi* tools response files restricted transactional memory    Intrinsics for Intel® Transactional Synchronization Extensions (Intel® TSX)    Intrinsics for Restricted Transactional Memory Operations restrictions on offloaded code    Restrictions on Offloaded Code Using a Pragma    Restrictions on Offloaded Code Using Shared Virtual Memory routine entry    falign-stack    option specifying the stack alignment to use on routines    opt-args-in-regs, Qopt-args-in-regs    option passing parameters in registers run-time performance    Overview: Tuning Performance    improving SA (static analysis) sample, offload code scalar replacement    scalar-rep, Qscalar-rep    opt-multi-version-aggressive, Qopt-multi-version-aggressive    option enabling during loop transformation    option using aggressive multi-versioning check for set stack size on coprocessors setjmp setting macros shared functions shared libraries shared memory shared memory, about using shared object    shared    option producing a dynamic shared scalars shared variables Short Vector Math Library (SVML) Intrinsics    Overview: Intrinsics for Short Vector Math Library (SVML) Functions    overview signed infinity signed zero simd    vectorization       simd       function annotations SIMD operations, C++ and Intel® Many Integrated Core (Intel® MIC) classes SIMD vectorization    simd, Qsimd    option disabling SMP systems source code analysis    Creating and Using Build Specification Files    build specification files specifying file names    Specifying Assembly Files    for assembly files specifying file names    Specifying Object Files    for object files stack    F (Windows* OS)    option specifying reserve amount stack alignment    Qsfalign    option specifying for functions stack checking routine    Gs    option controlling threshold for call of stack size, setting stack variables    ftrapuv, Qtrapuv    option initializing to NaN standard directories    X    option removing from include search path standards conformance    Conformance to the C Standard    Conformance to the C++ Standard static analysis    Using Static Analysis    option enabling       diag-enable sc, Qdiag-enable:sc       diag, Qdiag    option specifying directory for results of    option specifying level of messages       diag-enable sc, Qdiag-enable:sc       diag, Qdiag static analysis    Creating and Using Build Specification Files    build specification files static analysis    Using Static Analysis    Creating and Using Build Specification Files    Static Analysis Overview    initial setup    injection utility    inspxe-inject utility    inspxe-runsc utility    inspxe-wrap utility    overview    wrapper utility static libraries    Creating Libraries    option invoking tool to generate Streaming SIMD Extensions streaming stores    opt-streaming-stores, Qopt-streaming-stores    option generating for optimization subnormal numbers subroutines in the OpenMP* run-time library    OpenMP* Run-time Library Routines    for OpenMP*    parallel run-time Supplemental Streaming SIMD Extensions 3    Absolute Value Intrinsics    Addition Intrinsics    Concatenate Intrinsics    Multiplication Intrinsics    Negation Intrinsics    Overview: Supplemental Streaming SIMD Extensions 3 (SSSE3)    Shuffle Intrinsics    Subtraction Intrinsics    absolute value intrinsics    addition intrinsics    concatenate intrinsics    multiplication intrinsics    negation intrinsics       Negation Intrinsics       _mm_sign_epi16       _mm_sign_epi32       _mm_sign_epi8       _mm_sign_pi16       _mm_sign_pi32       _mm_sign_pi8    overview    shuffle intrinsics       _mm_shuffle_epi8       _mm_shuffle_pi8    subtraction intrinsics       Subtraction Intrinsics       _mm_hsub_epi16       _mm_hsub_epi32       _mm_hsub_pi16       _mm_hsub_pi32       _mm_hsubs_epi16       _mm_hsubs_pi16 supported tools SVML symbol names    Quse-msasm-symbols    option using dollar sign when producing symbol visibility    fvisibility    option specifying synchronization    Auto-Parallelization Overview    parallel processing model for    thread sleep time synchronization between cpu and target target    Applying the target Attribute to Multiple Declarations    Managing Memory Allocation for Pointer Variables    applying to multiple declarations    memory management target-specific code, writing    Overview: Using a Pragma    Writing Target-Specific Code Using a Pragma    Writing Target-Specific Code with _Cilk_offload targeting    Targeting Processors Manually    processors manually template instantiation test prioritization tool    examples    options    requirements thread affinity    Thread Affinity Interface (Linux* and Windows*)    option specifying thread pooling thread-local storage thread-private variables threaded applications    tcheck, Qtcheck    option enabling analysis of threshold control for auto-parallelization    OpenMP* Run-time Library Routines    Programming Guidelines for Vectorization    OpenMP* routines for    reordering timing offload regions tool options    PGO Tools Overview    code coverage tool    profmerge    proforder    test prioritization tools    PGO Tools Overview    option passing options to    option specifying directory for supporting topology maps traceback information    traceback    option providing transcendental functions    fast-transcendentals, Qfast-transcendentals    option replacing calls to transferring data asynchronously tselect tool    Qcov-gen    Qcov-dir    Qcov-file    option producing an instrumented file for    option specifying a directory for profiling output for    option specifying a file name for summary files for unvectorizable copy unwind information    fasynchronous-unwind-tables    option determining where precision occurs user functions    Compiler Directed Inline Expansion of Functions    Developer Directed Inline Expansion of User Functions    auto-parallelization    dynamic libraries    OpenMP*    profile-guided optimization       Profile an Application       Profile Function or Loop Execution Time using Intel® Performance Libraries Using OpenMP* utilities    PGO Tools Overview    profmerge    proforder valarray implementation    Using Intel's valarray Implementation    compiling code    using in code value-profiling    Resetting the Dynamic Profile Counters    Resetting Profile Information variable length arrays    Qvla    option enabling variables    fzero-initialized-in-bss , Qzero-initialized-in-bss    no-bss-init, Qnobss-init    fkeep-static-consts, Qkeep-static-consts    Placing Variables and Functions on the Coprocessor    Special Cases    option placing explicitly zero-initialized in DATA section       fzero-initialized-in-bss , Qzero-initialized-in-bss       no-bss-init, Qnobss-init    option placing uninitialized in DATA section    option saving always    placing on the coprocessor    thread-private variables, moving data from one to another variables, shared vector copy    Programming Guidelines for Vectorization    programming guidelines vector operations vectorization    Using Automatic Vectorization    vec, Qvec    vec-threshold, Qvec-threshold    compiler directives, pragmas    compiler options    keywords    obstacles    option disabling    option setting threshold for loops    speed-up    what is Vectorization    Function Annotations and the SIMD Directive for Vectorization    simd    User-mandated or SIMD Vectorization    language support    pragma simd    SIMD    user-mandated Vectorization    Function Annotations and the SIMD Directive for Vectorization    directive Vectorization    Function Annotations and the SIMD Directive for Vectorization    pragma vectorizer    vec-report, Qvec-report    option controlling diagnostics reported by vectorizing    Programming Guidelines for Vectorization    loops       Profile-Guided Optimizations Overview       Loop Constructs version    sox, Qsox    option saving in executable or object file visibility declaration attribute warnings    Werror, WX    Werror-all    option changing to errors       Werror, WX       Werror-all warnings and errors whole program analysis worker thread worksharing    OpenMP* Directives and Clauses Summary    Auto-Parallelization Overview xiar    About Creating Offload Libraries with xiar and xild    IPO-Related Performance Issues    Creating a Library from IPO Objects xild    About Creating Offload Libraries with xiar and xild    IPO-Related Performance Issues    Interprocedural Optimization (IPO) Overview    Creating a Library from IPO Objects xilib xilibtool xilink    IPO-Related Performance Issues    Interprocedural Optimization (IPO) Overview    Creating a Library from IPO Objects