StackOverflow Questions for Tag: intrinsics

Steve Burns

Reputation: 319

What is the inverse of "_mm256_cvtepi16_epi32"

x86g++intrinsicsavxavx2

Score: 6

Answers: 1

Gabriel Lim

Reputation: 13

Output errors when using libmvec intrinsics for trigo functions manually (like cosf)

c++gccglibcsseintrinsics

Score: 1

Answers: 1

Serge Rogatch

Reputation: 15020

__assume() seems to cause an internal error in NVCC: "Call has wrong number of parameters..."

visual-c++optimizationcudaintrinsicsnvcc

Score: 2

Answers: 2

nckm

Reputation: 133

How to merge two YMM registers into single ZMM but interleave?

assemblyintrinsicsavx512

Score: 0

Answers: 0

Slava.In

Reputation: 1059

What is dollar sign syntax in TypeScript?

typescripttypesintrinsicstypescript-utility

Score: 0

Answers: 2

Sofiane Benzait

Reputation: 39

How to have access to pointer to pointer to varying data (T**) using ISPC intel compiler

cintrinsicsavxispc

Score: 1

Answers: 1

E_1996

Reputation: 89

C++ AVX2 custom functions (e.g., "exp") not working on Windows (but work on Linux)

c++rcppintrinsicsavxavx2

Score: 0

Answers: 0

E_1996

Reputation: 89

C++ AVX2 Function Pointers/std::function not working on Windows (but work on Linux)

c++rcppintrinsicsavx2

Score: 1

Answers: 0

wangt13

Reputation: 1215

Failed to use GNU MIPS builtin functions of vector (SIMD)

cmipsgnusimdintrinsics

Score: 0

Answers: 1

Prunus Persica

Reputation: 1203

memcpy beats SIMD intrinsics

c++performancearmsimdintrinsics

Score: 0

Answers: 2

Christoph Diegelmann

Reputation: 2044

Fallback implementation for conflict detection in AVX2

c++x86intrinsicsavx2avx512

Score: 13

Answers: 1

Eric Thoma

Reputation: 6145

How do I use compiler intrinsic __fmul_?

ccudaintrinsics

Score: 1

Answers: 2

Levi Gibson

Reputation: 61

How to vectorise multiplication of an int8 array by an int16 constant, widening to int32 result array, in C (AVX2)

cx86simdintrinsicsavx2

Score: 5

Answers: 2

user1196549

Reputation:

Emulating byte-shifts on 32 bytes with AVX (lane-crossing)

c++simdintrinsicssse2avx2

Score: 12

Answers: 3

Thomas Lavergne

Reputation: 38

vfmlalq_low_f16 and vfmlalq_high_f16 not setting their first operand to the result

armintrinsicsneon

Score: 0

Answers: 1

Sai Charan Marrivada

Reputation: 35

Is this a gcc bug? Function returns 0 when looping an int* over elements of a __m256i

cgccx86intrinsicsavx

Score: 0

Answers: 3

SapphireSun

Reputation: 9388

SIMD: Accumulate Adjacent Pairs

c++ssesimdintrinsicsavx

Score: 3

Answers: 1

alco

Reputation: 1

Access violation when performing matrix product using SIMD in Rust

rustlinear-algebrasimdsseintrinsics

Score: 0

Answers: 1

Baaing Cow

Reputation: 1512

Multiply vectors of 32 bit integers, taking only high 32 bits

c++intrinsicslow-levelavx512

Score: 2

Answers: 2

Astranged T'fyer

Reputation: 63

Using SIMD To Parallelize Matrix Multiplication For A 4x4, Row-Major Matrix

cmatrix-multiplicationintrinsicsavx

Score: 1

Answers: 1

PreviousPage 1Next

StackOverflow Questions for Tag: intrinsics

What is the inverse of &quot;_mm256_cvtepi16_epi32&quot;

Output errors when using libmvec intrinsics for trigo functions manually (like cosf)

__assume() seems to cause an internal error in NVCC: &quot;Call has wrong number of parameters...&quot;

How to merge two YMM registers into single ZMM but interleave?

What is dollar sign syntax in TypeScript?

How to have access to pointer to pointer to varying data (T**) using ISPC intel compiler

C++ AVX2 custom functions (e.g., &quot;exp&quot;) not working on Windows (but work on Linux)

C++ AVX2 Function Pointers/std::function not working on Windows (but work on Linux)

Failed to use GNU MIPS builtin functions of vector (SIMD)

memcpy beats SIMD intrinsics

Fallback implementation for conflict detection in AVX2

How do I use compiler intrinsic __fmul_?

How to vectorise multiplication of an int8 array by an int16 constant, widening to int32 result array, in C (AVX2)

Emulating byte-shifts on 32 bytes with AVX (lane-crossing)

vfmlalq_low_f16 and vfmlalq_high_f16 not setting their first operand to the result

Is this a gcc bug? Function returns 0 when looping an int* over elements of a __m256i

SIMD: Accumulate Adjacent Pairs

Access violation when performing matrix product using SIMD in Rust

Multiply vectors of 32 bit integers, taking only high 32 bits

Using SIMD To Parallelize Matrix Multiplication For A 4x4, Row-Major Matrix

What is the inverse of "_mm256_cvtepi16_epi32"

__assume() seems to cause an internal error in NVCC: "Call has wrong number of parameters..."

C++ AVX2 custom functions (e.g., "exp") not working on Windows (but work on Linux)