diff options
| author | Ruslan Andreev <kels9009@gmail.com> | 2021-06-15 14:04:30 +0000 |
|---|---|---|
| committer | Austin Clements <austin@google.com> | 2021-09-07 20:27:30 +0000 |
| commit | 23f4f0db682fad0c8d61a5b5cdbdbad4cf1cd41f (patch) | |
| tree | 2c3d076097f9ff7e1289bb3e0623446694e7383c /src/cmd/internal/obj | |
| parent | d92101f452e10680ad4c8af2d5ad40d940b59214 (diff) | |
| download | go-23f4f0db682fad0c8d61a5b5cdbdbad4cf1cd41f.tar.xz | |
cmd/compile: add prefetch intrinsic support
This CL provide new intrinsics to emit prefetch instructions for AMD64
and ARM64 platforms:
Prefetch - prefetches data from memory address to cache;
PrefetchStreamed - prefetches data from memory address, with a hint
that this data is being streamed.
This patch also provides prefetch calls pointed by RSC inside scanobject
and greyobject of GC mark logic.
Performance results provided by Michael:
https://perf.golang.org/search?q=upload:20210901.9
Benchmark parameters:
tree2 -heapsize=1000000000 -cpus=8
tree -n=18
parser
peano
Benchmarks AMD64 (Xeon - Cascade Lake):
name old time/op new time/op delta
Tree2-8 36.1ms ± 6% 33.4ms ± 5% -7.65% (p=0.000 n=9+9)
Tree-8 326ms ± 1% 324ms ± 1% -0.44% (p=0.006 n=9+10)
Parser-8 2.75s ± 1% 2.71s ± 1% -1.47% (p=0.008 n=5+5)
Peano-8 63.1ms ± 1% 63.0ms ± 1% ~ (p=0.730 n=9+9)
[Geo mean] 213ms 207ms -2.45%
Benchmarks ARM64 (Kunpeng 920):
name old time/op new time/op delta
Tree2-8 50.3ms ± 8% 44.1ms ± 5% -12.24% (p=0.000 n=10+9)
Tree-8 494ms ± 1% 493ms ± 1% ~ (p=0.684 n=10+10)
Parser-8 3.99s ± 1% 3.93s ± 1% -1.37% (p=0.016 n=5+5)
Peano-8 84.4ms ± 0% 84.1ms ± 1% ~ (p=0.068 n=8+10)
[Geo mean] 302ms 291ms -3.67%
Change-Id: I43e10bc2f9512dc49d7631dd8843a79036fa43d0
Reviewed-on: https://go-review.googlesource.com/c/go/+/328289
Reviewed-by: Austin Clements <austin@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Diffstat (limited to 'src/cmd/internal/obj')
| -rw-r--r-- | src/cmd/internal/obj/arm64/obj7.go | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/src/cmd/internal/obj/arm64/obj7.go b/src/cmd/internal/obj/arm64/obj7.go index a043d0972c..ae8deede3a 100644 --- a/src/cmd/internal/obj/arm64/obj7.go +++ b/src/cmd/internal/obj/arm64/obj7.go @@ -51,6 +51,12 @@ var complements = []obj.As{ ACMNW: ACMPW, } +// noZRreplace is the set of instructions for which $0 in the To operand +// should NOT be replaced with REGZERO. +var noZRreplace = map[obj.As]bool{ + APRFM: true, +} + func (c *ctxt7) stacksplit(p *obj.Prog, framesize int32) *obj.Prog { // MOV g_stackguard(g), RT1 p = obj.Appendp(p, c.newprog) @@ -226,7 +232,7 @@ func progedit(ctxt *obj.Link, p *obj.Prog, newprog obj.ProgAlloc) { p.From.Type = obj.TYPE_REG p.From.Reg = REGZERO } - if p.To.Type == obj.TYPE_CONST && p.To.Offset == 0 { + if p.To.Type == obj.TYPE_CONST && p.To.Offset == 0 && !noZRreplace[p.As] { p.To.Type = obj.TYPE_REG p.To.Reg = REGZERO } |