StackOverflow Questions for Tag: neon

Steven Daniel Anderson

Reputation: 1443

How to Optimize 1024x1024 Matrix Multiplication in C to Match NumPy's Performance in M1 silicon

cnumpyoptimizationneon

Score: 0

Answers: 0

Nidhoegger

Reputation: 5232

NEON: Optimize code

carmneon

Score: 0

Answers: 1

Douglas B

Reputation: 832

Cannot compile simple program which uses ARM Neon for Cortex A53

armcross-compilingarm64neoncortex-a

Score: 0

Answers: 0

scoobydoo

Reputation: 123

typecast float32 to int16 using arm neon intrinsics

armneon

Score: 0

Answers: 1

jcdmelo

Reputation: 11

GCC error for ""vmull.u16 q7, d19, d8[0]" but not for ""vmull.u16 q7, d19, d7[0]"

assemblygccvectorizationsimdneon

Score: 1

Answers: 0

Pascal de Kloe

Reputation: 560

Bit scatter over multiple NEON registers

assemblyarmneon

Score: 0

Answers: 1

Lazyloper

Reputation: 41

What's the difference between LD3( multipule structure) and LD3 (single structure) in ARMv8-A structure

armloadneon

Score: 2

Answers: 1

Russell Newman

Reputation: 83

SIMD bit reordering of packed 12-bit integer array

csimdneonavx2pixelformat

Score: 3

Answers: 2

Zz Tux

Reputation: 658

What are the differences between `ld1`/`st1` and `ldr`/`str`, `ldp`/`stp` instructions when operating on one or two vector registers?

assemblyarmsimdarm64neon

Score: 0

Answers: 0

jcdmelo

Reputation: 1

ARM NEON: why is vector code slower than scalar?

armvectorizationneoncortex-a

Score: 0

Answers: 2

0xcaff

Reputation: 13681

Is there a difference between vst1.8 and vst1.32?

assemblyarmneon

Score: 1

Answers: 1

Yates Zhang

Reputation: 1

Neon intrinsic vsubq_f32?

neon

Score: 0

Answers: 0

ilp

Reputation: 21

ARM NEON Intrisics: Is using vmaxvq_s16() the fastest way to find max value in a int16x8 vector?

c++armvectorizationsimdneon

Score: 0

Answers: 1

Bogi

Reputation: 2618

Transpose 4x4 int32 matrix using NEON

assemblyarmintrinsicsneon

Score: 0

Answers: 1

J. Rehbein

Reputation: 117

Is it slow to branch on a memory offset incremented by vld1q in ARM NEON?

armsimdneon

Score: 0

Answers: 1

Aki Suihkonen

Reputation: 20037

Using Horizontal Neon intrinsics efficiently

assemblyinline-assemblyarm64intrinsicsneon

Score: 2

Answers: 1

maksdrv

Reputation: 3

ARM Assembly Vector addition

assemblyinline-assemblyarm64neon

Score: 0

Answers: 1

spaghetti_boy

Reputation: 1

Converting RGB to Grayscale with C ARM NEON

cneon

Score: 0

Answers: 0

TrentP

Reputation: 4722

Efficient C vectors for generic SIMD (SSE, AVX, NEON) test for zero matches. (find FP max absolute value and index)

cgccsimdsseneon

Score: 6

Answers: 3

ilp

Reputation: 21

ARM NEON Saturating Doubling Multiply C/C++ Intrisic for signed 8-bit integers

carmsimdneon

Score: 2

Answers: 0

PreviousPage 4Next

StackOverflow Questions for Tag: neon

How to Optimize 1024x1024 Matrix Multiplication in C to Match NumPy&#39;s Performance in M1 silicon

NEON: Optimize code

Cannot compile simple program which uses ARM Neon for Cortex A53

typecast float32 to int16 using arm neon intrinsics

GCC error for &quot;&quot;vmull.u16 q7, d19, d8[0]&quot; but not for &quot;&quot;vmull.u16 q7, d19, d7[0]&quot;

Bit scatter over multiple NEON registers

What&#39;s the difference between LD3( multipule structure) and LD3 (single structure) in ARMv8-A structure

SIMD bit reordering of packed 12-bit integer array

What are the differences between `ld1`/`st1` and `ldr`/`str`, `ldp`/`stp` instructions when operating on one or two vector registers?

ARM NEON: why is vector code slower than scalar?

Is there a difference between vst1.8 and vst1.32?

Neon intrinsic vsubq_f32?

ARM NEON Intrisics: Is using vmaxvq_s16() the fastest way to find max value in a int16x8 vector?

Transpose 4x4 int32 matrix using NEON

Is it slow to branch on a memory offset incremented by vld1q in ARM NEON?

Using Horizontal Neon intrinsics efficiently

ARM Assembly Vector addition

Converting RGB to Grayscale with C ARM NEON

Efficient C vectors for generic SIMD (SSE, AVX, NEON) test for zero matches. (find FP max absolute value and index)

ARM NEON Saturating Doubling Multiply C/C++ Intrisic for signed 8-bit integers

How to Optimize 1024x1024 Matrix Multiplication in C to Match NumPy's Performance in M1 silicon

GCC error for ""vmull.u16 q7, d19, d8[0]" but not for ""vmull.u16 q7, d19, d7[0]"

What's the difference between LD3( multipule structure) and LD3 (single structure) in ARMv8-A structure