Hi Peter, Please note that versions devel *go1.20-bcd44b61d3*, *1.19.1*, and *1.18.6* show times in the *4xxx ns/op* range for *BenchmarkSliceOfArray* while all the versions of *1.19* and *1.18* show times in the *2xxx ns/op* range.
As noted earlier in this thread, the regression is seen on *ARM64* and not *AMD64*. This time I have only included only results for *BenchmarkSliceOfArray*. The benchmarks for *BenchmarkSliceOfInt* do not exhibit regression. go version *devel go1.20-bcd44b61d3* Tue Sep 20 16:21:31 2022 +0000 darwin/arm64 BenchmarkSliceOfArray 262800 *4552* ns/op 16384 B/op 1 allocs/op go version *go1.19.1* darwin/arm64 BenchmarkSliceOfArray 229941 *4607* ns/op 16384 B/op 1 allocs/op go version *go1.19* darwin/arm64 BenchmarkSliceOfArray 449023 *2580* ns/op 16384 B/op 1 allocs/op go version *go1.18.6* darwin/arm64 BenchmarkSliceOfArray 239430 *4377* ns/op 16384 B/op 1 allocs/op go version *go1.18.5* darwin/arm64 BenchmarkSliceOfArray 506563 *2349* ns/op 16384 B/op 1 allocs/op go version *go1.18.4* darwin/arm64 BenchmarkSliceOfArray 508051 *2362* ns/op 16384 B/op 1 allocs/op go version *go1.18.3* darwin/arm64 BenchmarkSliceOfArray 431294 *2357* ns/op 16384 B/op 1 allocs/op go version *go1.18.2* darwin/arm64 BenchmarkSliceOfArray 425918 *2715* ns/op 16384 B/op 1 allocs/op go version *go1.18.1* darwin/arm64 BenchmarkSliceOfArray 434580 *2351* ns/op 16384 B/op 1 allocs/op go version *go1.18* darwin/arm64 BenchmarkSliceOfArray 415366 *2482* ns/op 16384 B/op 1 allocs/op On Tuesday, September 20, 2022 at 12:53:40 PM UTC-4 peterGo wrote: > Jan, > > An obvious typo. Read my original message: "I am unable to reproduce your > results on AMD64" > > peter > > On Tuesday, September 20, 2022 at 12:14:32 PM UTC-4 Jan Mercl wrote: > >> On Tue, Sep 20, 2022 at 6:02 PM peterGo <go.pe...@gmail.com> wrote: >> >> > Yes, I read that too. A fundamental tenet of science is >> reproducibility. I was able to reproduce the AMD64 results and documented >> it. A step forward. >> >> 5:24 PM (45 minutes ago) > I am unable to reproduce your results on AMD64. >> 6:02 PM (7 minutes ago) > I was able to reproduce the AMD64 results >> and documented it. >> > -- You received this message because you are subscribed to the Google Groups "golang-nuts" group. To unsubscribe from this group and stop receiving emails from it, send an email to golang-nuts+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/golang-nuts/7a9b8be8-7f8a-48ac-81ab-24c0780009d9n%40googlegroups.com.