StackOverflow Questions for Tag: memory-bandwidth

smz

Reputation: 505

Tracking DRAM traffic in AMD Zen 2 (Rome)

profilingperfamd-processormemory-bandwidth

Score: 2

Answers: 1

aggieNick02

Reputation: 2787

Why is Skylake so much better than Broadwell-E for single-threaded memory throughput?

performancex86cpu-architecturebenchmarkingmemory-bandwidth

Score: 19

Answers: 2

TinyOlap

Reputation: 47

What memory bandwidth utilisation to expect? And why does multi-threading/multi-processing make it worse?

cmultithreadingmultitaskingmemory-bandwidth

Score: 2

Answers: 2

user27594645

Reputation: 17

Does enabling compression in thrift helps memory bandwidth bottleneck if you have low cpu util and network util?

compressionrpcthriftthrift-protocolmemory-bandwidth

Score: 0

Answers: 0

xealits

Reputation: 4566

Why sysbench memory read benchmark shows higher bandwidth than the theoretical limit?

memorybenchmarkingbandwidthmemory-bandwidth

Score: 2

Answers: 1

Hari Krishna

Reputation: 109

What is difference between mem copy and full copy in lmbench3?

benchmarkingarm64bandwidthmemory-bandwidth

Score: 0

Answers: 0

Kensmosis

Reputation: 115

Can't seem to achieve anywhere near my GPU global memory bandwidth in OpenCL

openclgpgpuamd-gpuopencl-cmemory-bandwidth

Score: 0

Answers: 1

user25664889

Reputation: 53

Why does a for-loop copy not achieve peak CPU-RAM bandwidth on one core?

performanceoptimizationx86-64bandwidthmemory-bandwidth

Score: 0

Answers: 1

Bruce Merry

Reputation: 790

Not getting any cache-pollution benefit from PREFETCHNTA on Zen 3

x86-64cpu-cacheamd-processorprefetchmemory-bandwidth

Score: 1

Answers: 1

Nitin Malapally

Reputation: 648

Simple streaming loop shows higher effective B/W than DRAM B/W for small enough problems

c++linuxperformance-testingmicrobenchmarkmemory-bandwidth

Score: 0

Answers: 1

Kailash gogineni

Reputation: 13

How to calculate the L3 cache bandwidth by using the performance counters linux?

linuxperformancecountercpu-cacheperfmemory-bandwidth

Score: 1

Answers: 1

platelet

Reputation: 185

There is a huge speed difference between reading and writing in DRAM, is this normal?

assemblymemoryx86benchmarkingmemory-bandwidth

Score: 2

Answers: 0

Albert Caldas

Reputation: 135

Why accessing an array of int8_t is not faster than int32_t, due to cache?

cachingbenchmarkingcpu-cachestridememory-bandwidth

Score: 1

Answers: 1

einpoklum

Reputation: 132128

Load/stores per cycle for recent CPU architecture generations

performancex86cpucpu-architecturememory-bandwidth

Score: 3

Answers: 1

Frontier_Setter

Reputation: 649

Why using non-temporal store instructions cannot reduce memory bandwidth usage? (Writes seem to be generating extra reads)

x86cpu-architectureintelmemcpymemory-bandwidth

Score: 4

Answers: 0

Frontier_Setter

Reputation: 649

How do different monitoring tools calculate memory bandwidth?

performanceintelamd-processorintel-pmumemory-bandwidth

Score: 1

Answers: 0

TheAhmad

Reputation: 940

Workload Memory Bandwidth Comparison Inconsistency

x86perfmemory-accessintel-pmumemory-bandwidth

Score: 0

Answers: 0

Frontier_Setter

Reputation: 649

How to test the “random access bandwidth" of memory?

performancememorybenchmarkingbandwidthmemory-bandwidth

Score: 0

Answers: 1

veda

Reputation: 6614

CUDA: Memory performance, What is Global memory bandwidth

cudamemory-bandwidth

Score: 2

Answers: 1

Pouya

Reputation: 1959

Why vectorizing the loop over 64-bit elements does not have performance improvement over large buffers?

cperformancesimdiccmemory-bandwidth

Score: 41

Answers: 4

PreviousPage 1Next

StackOverflow Questions for Tag: memory-bandwidth

Tracking DRAM traffic in AMD Zen 2 (Rome)

Why is Skylake so much better than Broadwell-E for single-threaded memory throughput?

What memory bandwidth utilisation to expect? And why does multi-threading/multi-processing make it worse?

Does enabling compression in thrift helps memory bandwidth bottleneck if you have low cpu util and network util?

Why sysbench memory read benchmark shows higher bandwidth than the theoretical limit?

What is difference between mem copy and full copy in lmbench3?

Can&#39;t seem to achieve anywhere near my GPU global memory bandwidth in OpenCL

Why does a for-loop copy not achieve peak CPU-RAM bandwidth on one core?

Not getting any cache-pollution benefit from PREFETCHNTA on Zen 3

Simple streaming loop shows higher effective B/W than DRAM B/W for small enough problems

How to calculate the L3 cache bandwidth by using the performance counters linux?

There is a huge speed difference between reading and writing in DRAM, is this normal?

Why accessing an array of int8_t is not faster than int32_t, due to cache?

Load/stores per cycle for recent CPU architecture generations

Why using non-temporal store instructions cannot reduce memory bandwidth usage? (Writes seem to be generating extra reads)

How do different monitoring tools calculate memory bandwidth?

Workload Memory Bandwidth Comparison Inconsistency

How to test the “random access bandwidth&quot; of memory?

CUDA: Memory performance, What is Global memory bandwidth

Why vectorizing the loop over 64-bit elements does not have performance improvement over large buffers?

Can't seem to achieve anywhere near my GPU global memory bandwidth in OpenCL

How to test the “random access bandwidth" of memory?