MAA
-
Posts
113 -
Joined
-
Last visited
-
Days Won
1
Recent Profile Visitors
3286 profile views
MAA's Achievements
-
missing a lot of information, incorrect dram latency... is this "fine"?
-
New cache and memory benchmarks in AIDA64 v3.00
MAA replied to Fiery's topic in Benchmarking, system performance
Hello, Why is the Memory Write speed 79 percent faster than the Memory Read speed?
-
For now I suggest using uvg266 https://github.com/ultravideo/uvg266 unlike x265, uvg266 scales very well to the number of cores:
-
Hello, Why is the Memory Write speed 67 percent faster than the Memory Read speed?
-
Hello, Suggestion - release a standalone CPU/GPU benchmark based on your ray tracing engine (from FP32/FP64 Ray-Trace benchmark) with visualization (similar to Cinebench 2024) this will increase mentions and popularity of AIDA
-
what exact method do you use to measure flops/iops? matrix multiplication or something else?
-
We will add the Bytes per Clock (BPC) bandwidth option to the right-click context menu in the next AIDA64 beta update In this case, the "Latency" should also switch to "clocks"
-
As for the per core request, I'm afraid our multi-threaded bandwidth benchmarks do not expose the per-core performance results, so we cannot show them on the UI. But modern processors have different cores (Intel P/E, Zen 5/5c), and it would be interesting to be able to get results for different types of cores
-
Hello, please add the ability to switch results between GB/sec and bytes/clock please add the ability to show results per core
-
New cache and memory benchmarks in AIDA64 v3.00
MAA replied to Fiery's topic in Benchmarking, system performance
Hello, why is L2 BW lower than L3 BW?
-
Still no plans to make an NPU benchmark?
-
in that case this code is not suitable for the reference benchmark
-
Why is Threadripper 7975WX's FPU Mandel score worse than 3970X again?
-
https://en.wikipedia.org/wiki/Raptor_Lake#Instability_and_degradation_issue
-
in that case both results should be published
