StackOverflow Questions for Tag: memory-bandwidth

Tim

Reputation: 1006

What specifically marks an x86 cache line as dirty - any write, or is an explicit change required?

x86x86-64cpu-architecturecpu-cachememory-bandwidth

Score: 17

Answers: 3

user2403221

Reputation: 445

C++ Optimize Memory Read Speed

c++performancesimdapple-m1memory-bandwidth

Score: 3

Answers: 3

BeeOnRope

Reputation: 65046

Can the Intel performance monitor counters be used to measure memory bandwidth?

performancex86intel-pmumemory-bandwidth

Score: 15

Answers: 5

harnamc

Reputation: 551

Clarification on GPU bandwidth in relation to PCI Express slots transfer rate (v1.x - x16)

gpubandwidthdata-transfervideo-cardmemory-bandwidth

Score: 2

Answers: 1

Noah

Reputation: 1759

Understanding factors in latency bounded memcpy/memset x86_64

x86-64intelcpu-architecturememcpymemory-bandwidth

Score: 2

Answers: 0

AS425

Reputation: 11

Is memory a bottleneck in matrix addition (SIMD Instructions)?

cmatrixsimdavxmemory-bandwidth

Score: 0

Answers: 1

AS425

Reputation: 11

Adding Array SIMD vs Unrolling

csimdavxmemory-bandwidth

Score: 1

Answers: 0

x5444

Reputation: 21

OpenCL Memory Bandwidth/Coalescing

c++gpuopenclgpgpumemory-bandwidth

Score: 2

Answers: 1

Armen Avetisyan

Reputation: 1258

Roofline model: calculating operational intensity

c++performancememory-bandwidthroofline

Score: 10

Answers: 1

Gabe

Reputation: 103

How to efficiently vectorize polynomial computation with condition (roofline model)

eigenintrinsicsavx2auto-vectorizationmemory-bandwidth

Score: 0

Answers: 1

Steve Linton

Reputation: 369

Does NUMA impact memory bandwidth, or just latency?

numamemory-bandwidth

Score: 4

Answers: 1

Faruk NANE

Reputation: 41

Why is performance gain of C# SIMD low with larger arrays than tiny arrays?

c#performancevectorizationsimdmemory-bandwidth

Score: 2

Answers: 1

user4859735

Reputation: 103

MOVSD performance depends on arguments

performancedelphiassemblyx86memory-bandwidth

Score: 10

Answers: 1

yeeha

Reputation: 138

what does STREAM memory bandwidth benchmark really measure?

benchmarkingcpu-architecturemicrobenchmarkmemory-bandwidth

Score: 9

Answers: 3

user14717

Reputation: 5171

Cannot interpret memory bandwidth numbers

performancex86memory-bandwidth

Score: 1

Answers: 1

WannabeArchitect

Reputation: 1176

Memory-bandwidth limited and computation-limited applications of GPU

gpgpugpumemory-bandwidth

Score: 3

Answers: 0

einpoklum

Reputation: 132108

How do I calculate memory bandwidth on a given (Linux) system, from the shell?

memorysysfsmemory-bandwidth

Score: 4

Answers: 2

nomadlx

Reputation: 155

When do I have to multiply by 2 to compute memory bandwidth

cudamemory-bandwidth

Score: 1

Answers: 1

joz

Reputation: 349

Can x86's lock prefix on uncacheable memory cause a Denial of Service on memory bandwidth?

x86lockingatomiccpu-architecturememory-bandwidth

Score: 5

Answers: 0

JohnAl

Reputation: 1084

Any optimization for random access on a very big array when the value in 95% of cases is either 0 or 1?

c++arraysperformanceoptimizationmemory-bandwidth

Score: 135

Answers: 13

PreviousPage 3Next

StackOverflow Questions for Tag: memory-bandwidth

What specifically marks an x86 cache line as dirty - any write, or is an explicit change required?

C++ Optimize Memory Read Speed

Can the Intel performance monitor counters be used to measure memory bandwidth?

Clarification on GPU bandwidth in relation to PCI Express slots transfer rate (v1.x - x16)

Understanding factors in latency bounded memcpy/memset x86_64

Is memory a bottleneck in matrix addition (SIMD Instructions)?

Adding Array SIMD vs Unrolling

OpenCL Memory Bandwidth/Coalescing

Roofline model: calculating operational intensity

How to efficiently vectorize polynomial computation with condition (roofline model)

Does NUMA impact memory bandwidth, or just latency?

Why is performance gain of C# SIMD low with larger arrays than tiny arrays?

MOVSD performance depends on arguments

what does STREAM memory bandwidth benchmark really measure?

Cannot interpret memory bandwidth numbers

Memory-bandwidth limited and computation-limited applications of GPU

How do I calculate memory bandwidth on a given (Linux) system, from the shell?

When do I have to multiply by 2 to compute memory bandwidth

Can x86&#39;s lock prefix on uncacheable memory cause a Denial of Service on memory bandwidth?

Any optimization for random access on a very big array when the value in 95% of cases is either 0 or 1?

Can x86's lock prefix on uncacheable memory cause a Denial of Service on memory bandwidth?