StackRating

An Elo-based rating system for Stack Overflow
Home   |   About   |   Stats and Analysis   |   Get a Badge
Rating Stats for

John D McCalpin

Rating
1522.72 (27,116th) 		Reputation
571 (245,436th)
Page: 1
Title Δ
Multiply-add vectorization slower with AVX than with SSE -2.47
Using linux perf tool to measure the amount of times the CPU has to... +4.77
Slowing down CPU Frequency by imposing memory stress -1.25
cache coherency (particular case of cache physically tagged) -3.31
Can you directly access the cache using assembly? -0.15
Do any CPU architectures use Metadata? -3.32
Does NUMA impact memory bandwidth, or just latency? 0.00
Why does not AVX further improve the performance compared with SSE2? +0.52
How many values can be stored per physical address in Memory? 0.00
Assign a Server CPU core to execute a specific call 0.00
Is it possible to test if a number is either even or '1', u... -1.44
Using rdmsr/rdpmc for branch prediction accuracy +3.71
Benchmarking memory copy in a single shot 0.00
What happens to expected memory semantics (such as read after write... +4.18
Are REP instructions considered vector operations? 0.00
Difference between profiling and dignostics(performance counters an... 0.00
Can a lower level cache have higher associativity and still hold in... +4.69
What causes this high variability in cycles for a simple tight loop... +3.85
Why do newer Intel CPUs not suppert performance counter for stalled... +4.34
what does STREAM memory bandwidth benchmark really measure? +4.63
how to do mmap for cacheable PCIe BAR 0.00
Measuring TLB miss handling cost in x86-64 +3.97
Hardware prefetching in corei3 0.00
In what circumstances can large pages produce a speedup? 0.00
programatically disable hardware prefetching on AMD systems 0.00