_mm_fnmadd_sd
Multiply-adds negated scalar double-precision floating-point values of three float64 vectors. The corresponding FMA instruction is VFNMADD<XXX>SD, where XXX could be 132, 213, or 231.Syntaxextern...
View Article_mm256_min_epu8/16/32
Determines the minimum value between two vectors with packed unsigned byte/word/doubleword integers. The corresponding Intel® AVX2 instruction is VPMINUB, VPMINUW, or VPMINUD.Syntaxextern __m256i...
View Article_mm256_or_si256
Performs bitwise logical OR operation on signed integer vectors. The corresponding Intel® AVX2 instruction is VPOR.Syntaxextern __m256i _mm256_or_si256(__m256i s1, __m256i s2);Argumentss1signed integer...
View Article_mm256_mullo_epi16/32
Multiplies signed packed 16/32-bit integer data elements of two vectors and stores low bits. The corresponding Intel® AVX2 instruction is VPMULLW or VPMULLD.Syntaxextern __m256i...
View Article_mm256_subs_epi8/16
Subtracts the signed 8/16-bit integer data elements with saturation of two vectors. The corresponding Intel® AVX2 instruction is VPSUBSB or VPSUBSW.Syntaxextern __m256i _mm256_subs_epi8(__m256i s1,...
View Article_addcarry_u32(), _addcarry_u64()
Computes sum of two 32/64 bit wide unsigned integer values and a carry-in and returns the value of carry-out produced by the sum. The corresponding 4th Generation Intel® Core™ Processor extension...
View Article_mm_spflt
Sets performance monitoring filtering mask. Corresponding instruction is spflt. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).Syntaxextern unsigned...
View Article_mm512_extloadunpackhi_epi32/ _mm512_mask_extloadunpackhi_epi32
Loads high 64-byte-aligned portion of unaligned doubleword stream, unpacks mask-enabled elements that fall in that portion, and stores those elements in int32 vector. Corresponding instruction is...
View Article_mm512_cvtepi32lo_pd/ _mm512_mask_cvtepi32lo_pd
Converts int32 vector to float64 vector. Corresponding instruction is VCVTDQ2PD. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).SyntaxWithout...
View Article_mm512_xor_epi64/ _mm512_mask_xor_epi64
Bitwise XOR operation between int64 vectors. Corresponding instruction is VPXORQ. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).SyntaxWithout...
View Article_mm512_subsetb_epi32/ _mm512_mask_subsetb_epi32
Subtracts int32 vectors and sets borrow. The corresponding instruction is VPSUBSETBD. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).SyntaxWithout...
View Article_mm512_mulhi_epu32/ _mm512_mask_mulhi_epu32
Multiply uint32 vectors and store the high half of the result. The corresponding instruction is VMULHPU. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC...
View ArticleValgrind (Version 3.7.0) errors using Intel MKL 11 routines and Intel C++...
Hi,I'm fairly new in using valgrind and the Intel C++ Compiler and I got the following problem. I compiled and build an executable out of the following source code in example.cpp:#include "mkl.h"int...
View ArticleClik here to view.
The Chronicles of Phi - part 4 - Hyper-Thread Phalanx – tiled_HT2
The prior part (3) of this blog showed the effects of the first-level implementation of the Hyper-Thread Phalanx. The change in programming yielded 9.7% improvement in performance for the small model,...
View Articlequestions about intel C++ studio XE 2013
Q:intel C++ studio XE 2013 when does next version come out? Q:intel C++ studio XE 2013 does this c++ compiler come with any build tools? Q:intel C++ studio XE 2013 what can I do if I find a compiler...
View ArticleOptimization features.
Hello,I'd like to talk about two weird things in the optimization process of the compiler.#1 : sqrtsd seems preferred over sqrtpd... (just did a 30% performance boost by forcing the use of 2 sqrtpd...
View Articlefinstrument-functions, Qinstrument-functions
Determines whether function entry and exit points are instrumented.Architecture RestrictionsNot available on Intel® 64 architecture targeting Intel® MIC Architecture, or on IA-32 architecture targeting...
View Articleopt-streaming-cache-evict, Qopt-streaming-cache-evict
Specifies the cache eviction level to be used by the compiler for streaming loads and stores. This option only applies to Intel® MIC Architecture.Architecture RestrictionsOnly available on Intel® 64...
View Articleipp, Qipp
Tells the compiler to link to the some or all of the Intel® Integrated Performance Primitives (Intel® IPP) libraries.Architecture RestrictionsNot available on Intel® 64 architecture targeting Intel®...
View ArticleConditional compilation bug or feature ?
Hi,I have a software that has 2 versions of an implemented algorithm, so it used different versions of the same class (in my case its SSE vs AVX, but really, it's not relevant) in 2 different compiler...
View Article