Re:Hot Chips 2023: SiFive’s P870 Takes RISC-V Further
by pama on Monday September 04, 2023 @05:56PM
(#37385494)
Is there any good benchmark/comparison of the current risk-v boards for use in hobby projects?
[ Parent
| on HN ]
Re:Hot Chips 2023: SiFive’s P870 Takes RISC-V Further
by brucehoult on Monday September 04, 2023 @08:23PM
(#37386500)
If by "good" you mean "something that's probably about as good as Dhrystone or Coremark but a lot simpler and harder to game" then I've got a benchmark and quite a few results collected on various things over the last seven years here:
Re:Hot Chips 2023: SiFive’s P870 Takes RISC-V Further
by pama on Tuesday September 05, 2023 @10:10AM
(#37391867)
Thanks. So some of these cpu, say VisionFive 2 U74, start to look interesting.
Re:Hot Chips 2023: SiFive’s P870 Takes RISC-V Further
by pama on Wednesday September 06, 2023 @10:22PM
(#37413972)
Just noting for my own reference that the TH1520 is well within the interesting range.
Re:Hot Chips 2023: SiFive’s P870 Takes RISC-V Further
by OhMeadhbh on Tuesday September 05, 2023 @04:16PM
(#37397138)
Though... RISC-V support in gnu c and clang have evolved significantly over the last 5 years. Did you re-run any of the tests with more recent compilers? When we were doing benchmarking 5 years ago, it seemed we got slightly better performance every month as Palmer integrated improvements into the gnu toolchain. There were at least a couple months there where we REALLY didn't want to publish benchmarks because we were expecting the numbers to be noticeably better in n days.
Re:Hot Chips 2023: SiFive’s P870 Takes RISC-V Further
by brucehoult on Tuesday September 05, 2023 @09:53PM
(#37400494)
This is very straightforward code (which I wrote in 2016 before I'd even heard of RISC-V) that maps very cleanly and obviously to instructions and any gcc from the last 20 years will make essentially the same code. A large part of my goal when I wrote it was to make it far more impervious to compiler "improvements" and gaming that Dhrystone and Coremark -- and I think I succeeded very well.
The RISC-V B extension's `sh2add` and friends make a small difference -- that's basically the 2.7% gap between the VisionFive 2 and the HiFive Unmatched. If I disable Zba on the VF2 then the times are just about identical.