mirror of
https://github.com/golang/go
synced 2024-11-27 04:01:19 -07:00
771c57e68e
281 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
fanzha02
|
b182ba7fab |
cmd/compile: optimize codes with arm64 REV16 instruction
Optimize some patterns into rev16/rev16w instruction.
Pattern1:
(c & 0xff00ff00)>>8 | (c & 0x00ff00ff)<<8
To:
rev16w c
Pattern2:
(c & 0xff00ff00ff00ff00)>>8 | (c & 0x00ff00ff00ff00ff)<<8
To:
rev16 c
This patch is a copy of CL 239637, contributed by Alice Xu(dianhong.xu@arm.com).
Change-Id: I96936c1db87618bc1903c04221c7e9b2779455b3
Reviewed-on: https://go-review.googlesource.com/c/go/+/268377
Trust: fannie zhang <Fannie.Zhang@arm.com>
Run-TryBot: fannie zhang <Fannie.Zhang@arm.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
|
||
Cherry Zhang
|
6ae3b70ef2 |
cmd/compile: add clobberdeadreg mode
When -clobberdeadreg flag is set, the compiler inserts code that clobbers integer registers at call sites. This may be helpful for debugging register ABI. Only implemented on AMD64 for now. Change-Id: Ia203d3f891c30fd95d0103489056fe01d63a2899 Reviewed-on: https://go-review.googlesource.com/c/go/+/302809 Trust: Cherry Zhang <cherryyz@google.com> Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com> |
||
|
fanzha02
|
f5e6d3e879 |
cmd/compile: add rewrite rules for conditional instructions on arm64
This CL adds rewrite rules for CSETM, CSINC, CSINV, and CSNEG. By adding
these rules, we can save one instruction.
For example,
func test(cond bool, a int) int {
if cond {
a++
}
return a
}
Before:
MOVD "".a+8(RSP), R0
ADD $1, R0, R1
MOVBU "".cond(RSP), R2
CMPW $0, R2
CSEL NE, R1, R0, R0
After:
MOVBU "".cond(RSP), R0
CMPW $0, R0
MOVD "".a+8(RSP), R0
CSINC EQ, R0, R0, R0
This patch is a copy of CL 285694. Co-authored-by: JunchenLi
<junchen.li@arm.com>
Change-Id: Ic1a79e8b8ece409b533becfcb7950f11e7b76f24
Reviewed-on: https://go-review.googlesource.com/c/go/+/302231
Trust: fannie zhang <Fannie.Zhang@arm.com>
Run-TryBot: fannie zhang <Fannie.Zhang@arm.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
|
||
|
Cherry Zhang
|
8628bf9a97 |
cmd/compile: resurrect clobberdead mode
This CL resurrects the clobberdead debugging mode (CL 23924). When -clobberdead flag is set (TODO: make it GOEXPERIMENT?), the compiler inserts code that clobbers all dead stack slots that contains pointers. Mark windows syscall functions cgo_unsafe_args, as the code actually does that, by taking the address of one argument and passing it to cgocall. Change-Id: Ie09a015f4bd14ae6053cc707866e30ae509b9d6f Reviewed-on: https://go-review.googlesource.com/c/go/+/301791 Trust: Cherry Zhang <cherryyz@google.com> Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com> Reviewed-by: Than McIntosh <thanm@google.com> |
||
Meng Zhuo
|
afe517590c |
cmd/compile: loads from readonly globals into const for mips64x
Ref: CL 141118 Update #26498 Change-Id: If4ea55c080b9aa10183eefe81fefbd4072deaf3a Reviewed-on: https://go-review.googlesource.com/c/go/+/280646 Trust: Meng Zhuo <mzh@golangcn.org> Reviewed-by: Keith Randall <khr@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
erifan01
|
600259b099 |
cmd/compile: use depth first topological sort algorithm for layout
The current layout algorithm tries to put consecutive blocks together,
so the priority of the successor block is higher than the priority of
the zero indegree block. This algorithm is beneficial for subsequent
register allocation, but will result in more branch instructions.
The depth-first topological sorting algorithm is a well-known layout
algorithm, which has applications in many languages, and it helps to
reduce branch instructions. This CL applies it to the layout pass.
The test results show that it helps to reduce the code size.
This CL also includes the following changes:
1, Removed the primary predecessor mechanism. The new layout algorithm is
not very friendly to register allocator in some cases, in order to adapt
to the new layout algorithm, a new primary predecessor selection strategy
is introduced.
2, Since the new layout implementation may place non-loop blocks between
loop blocks, some adaptive modifications have also been made to looprotate
pass.
3, The layout also affects the results of codegen, so this CL also adjusted
several codegen tests accordingly.
It is inevitable that this CL will cause the code size or performance of a
few functions to decrease, but the number of cases it improves is much larger
than the number of cases it drops.
Statistical data from compilecmp on linux/amd64 is as follow:
name old time/op new time/op delta
Template 382ms ± 4% 382ms ± 4% ~ (p=0.497 n=49+50)
Unicode 170ms ± 9% 169ms ± 8% ~ (p=0.344 n=48+50)
GoTypes 2.01s ± 4% 2.01s ± 4% ~ (p=0.628 n=50+48)
Compiler 190ms ±10% 189ms ± 9% ~ (p=0.734 n=50+50)
SSA 11.8s ± 2% 11.8s ± 3% ~ (p=0.877 n=50+50)
Flate 241ms ± 9% 241ms ± 8% ~ (p=0.897 n=50+49)
GoParser 366ms ± 3% 361ms ± 4% -1.21% (p=0.004 n=47+50)
Reflect 835ms ± 3% 838ms ± 3% ~ (p=0.275 n=50+49)
Tar 336ms ± 4% 335ms ± 3% ~ (p=0.454 n=48+48)
XML 433ms ± 4% 431ms ± 3% ~ (p=0.071 n=49+48)
LinkCompiler 706ms ± 4% 705ms ± 4% ~ (p=0.608 n=50+49)
ExternalLinkCompiler 1.85s ± 3% 1.83s ± 2% -1.47% (p=0.000 n=49+48)
LinkWithoutDebugCompiler 437ms ± 5% 437ms ± 6% ~ (p=0.953 n=49+50)
[Geo mean] 615ms 613ms -0.37%
name old alloc/op new alloc/op delta
Template 38.7MB ± 1% 38.7MB ± 1% ~ (p=0.834 n=50+50)
Unicode 28.1MB ± 0% 28.1MB ± 0% -0.22% (p=0.000 n=49+50)
GoTypes 168MB ± 1% 168MB ± 1% ~ (p=0.054 n=47+47)
Compiler 23.0MB ± 1% 23.0MB ± 1% ~ (p=0.432 n=50+50)
SSA 1.54GB ± 0% 1.54GB ± 0% +0.21% (p=0.000 n=50+50)
Flate 23.6MB ± 1% 23.6MB ± 1% ~ (p=0.153 n=43+46)
GoParser 35.1MB ± 1% 35.1MB ± 2% ~ (p=0.202 n=50+50)
Reflect 84.7MB ± 1% 84.7MB ± 1% ~ (p=0.333 n=48+49)
Tar 34.5MB ± 1% 34.5MB ± 1% ~ (p=0.406 n=46+49)
XML 44.3MB ± 2% 44.2MB ± 3% ~ (p=0.981 n=50+50)
LinkCompiler 131MB ± 0% 128MB ± 0% -2.74% (p=0.000 n=50+50)
ExternalLinkCompiler 120MB ± 0% 120MB ± 0% +0.01% (p=0.007 n=50+50)
LinkWithoutDebugCompiler 77.3MB ± 0% 77.3MB ± 0% -0.02% (p=0.000 n=50+50)
[Geo mean] 69.3MB 69.1MB -0.22%
file before after Δ %
addr2line 4104220 4043684 -60536 -1.475%
api 5342502 5249678 -92824 -1.737%
asm 4973785 4858257 -115528 -2.323%
buildid 2667844 2625660 -42184 -1.581%
cgo 4686849 4616313 -70536 -1.505%
compile 23667431 23268406 -399025 -1.686%
cover 4959676 4874108 -85568 -1.725%
dist 3515934 3450422 -65512 -1.863%
doc 3995581 3925469 -70112 -1.755%
fix 3379202 3318522 -60680 -1.796%
link 6743249 6629913 -113336 -1.681%
nm 4047529 3991777 -55752 -1.377%
objdump 4456151 4388151 -68000 -1.526%
pack 2435040 2398072 -36968 -1.518%
pprof 13804080 13565808 -238272 -1.726%
test2json 2690043 2645987 -44056 -1.638%
trace 10418492 10232716 -185776 -1.783%
vet 7258259 7121259 -137000 -1.888%
total 113145867 111204202 -1941665 -1.716%
The situation on linux/arm64 is as follow:
name old time/op new time/op delta
Template 280ms ± 1% 282ms ± 1% +0.75% (p=0.000 n=46+48)
Unicode 124ms ± 2% 124ms ± 2% +0.37% (p=0.045 n=50+50)
GoTypes 1.69s ± 1% 1.70s ± 1% +0.56% (p=0.000 n=49+50)
Compiler 122ms ± 1% 123ms ± 1% +0.93% (p=0.000 n=50+50)
SSA 12.6s ± 1% 12.7s ± 0% +0.72% (p=0.000 n=50+50)
Flate 170ms ± 1% 172ms ± 1% +0.97% (p=0.000 n=49+49)
GoParser 262ms ± 1% 263ms ± 1% +0.39% (p=0.000 n=49+48)
Reflect 639ms ± 1% 650ms ± 1% +1.63% (p=0.000 n=49+49)
Tar 243ms ± 1% 245ms ± 1% +0.82% (p=0.000 n=50+50)
XML 324ms ± 1% 327ms ± 1% +0.72% (p=0.000 n=50+49)
LinkCompiler 597ms ± 1% 596ms ± 1% -0.27% (p=0.001 n=48+47)
ExternalLinkCompiler 1.90s ± 1% 1.88s ± 1% -1.00% (p=0.000 n=50+50)
LinkWithoutDebugCompiler 364ms ± 1% 363ms ± 1% ~ (p=0.220 n=49+50)
[Geo mean] 485ms 488ms +0.49%
name old alloc/op new alloc/op delta
Template 38.7MB ± 0% 38.8MB ± 1% ~ (p=0.093 n=43+49)
Unicode 28.4MB ± 0% 28.4MB ± 0% +0.03% (p=0.000 n=49+45)
GoTypes 169MB ± 1% 169MB ± 1% +0.23% (p=0.010 n=50+50)
Compiler 23.2MB ± 1% 23.2MB ± 1% +0.11% (p=0.000 n=40+44)
SSA 1.54GB ± 0% 1.55GB ± 0% +0.45% (p=0.000 n=47+49)
Flate 23.8MB ± 2% 23.8MB ± 1% ~ (p=0.543 n=50+50)
GoParser 35.3MB ± 1% 35.4MB ± 1% ~ (p=0.792 n=50+50)
Reflect 85.2MB ± 1% 85.2MB ± 0% ~ (p=0.055 n=50+47)
Tar 34.5MB ± 1% 34.5MB ± 1% +0.06% (p=0.015 n=50+50)
XML 43.8MB ± 2% 43.9MB ± 2% +0.19% (p=0.000 n=48+48)
LinkCompiler 137MB ± 0% 136MB ± 0% -0.92% (p=0.000 n=50+50)
ExternalLinkCompiler 127MB ± 0% 127MB ± 0% ~ (p=0.516 n=50+50)
LinkWithoutDebugCompiler 84.0MB ± 0% 84.0MB ± 0% ~ (p=0.057 n=50+50)
[Geo mean] 70.4MB 70.4MB +0.01%
file before after Δ %
addr2line 4021557 4002933 -18624 -0.463%
api 5127847 5028503 -99344 -1.937%
asm 5034716 4936836 -97880 -1.944%
buildid 2608118 2594094 -14024 -0.538%
cgo 4488592 4398320 -90272 -2.011%
compile 22501129 22213592 -287537 -1.278%
cover 4742301 4713573 -28728 -0.606%
dist 3388071 3365311 -22760 -0.672%
doc 3802250 3776082 -26168 -0.688%
fix 3306147 3216939 -89208 -2.698%
link 6404483 6363699 -40784 -0.637%
nm 3941026 3921930 -19096 -0.485%
objdump 4383330
|
||
Josh Bleecher Snyder
|
43d5f213e2 |
cmd/compile: optimize multi-register shifts on amd64
amd64 can shift in bits from another register instead of filling with 0/1. This pattern is helpful when implementing 128 bit shifts or arbitrary length shifts. In the standard library, it shows up in pure Go math/big. Benchmarks results on amd64 with -tags=math_big_pure_go. name old time/op new time/op delta NonZeroShifts/1/shrVU-8 4.45ns ± 3% 4.39ns ± 1% -1.28% (p=0.000 n=30+27) NonZeroShifts/1/shlVU-8 4.13ns ± 4% 4.10ns ± 2% ~ (p=0.254 n=29+28) NonZeroShifts/2/shrVU-8 5.55ns ± 1% 5.63ns ± 2% +1.42% (p=0.000 n=28+29) NonZeroShifts/2/shlVU-8 5.70ns ± 2% 5.14ns ± 1% -9.82% (p=0.000 n=29+28) NonZeroShifts/3/shrVU-8 6.79ns ± 2% 6.35ns ± 2% -6.46% (p=0.000 n=28+29) NonZeroShifts/3/shlVU-8 6.69ns ± 1% 6.25ns ± 1% -6.60% (p=0.000 n=28+27) NonZeroShifts/4/shrVU-8 7.79ns ± 2% 7.06ns ± 2% -9.48% (p=0.000 n=30+30) NonZeroShifts/4/shlVU-8 7.82ns ± 1% 7.24ns ± 1% -7.37% (p=0.000 n=28+29) NonZeroShifts/5/shrVU-8 8.90ns ± 3% 7.93ns ± 1% -10.84% (p=0.000 n=29+26) NonZeroShifts/5/shlVU-8 8.68ns ± 1% 7.92ns ± 1% -8.76% (p=0.000 n=29+29) NonZeroShifts/10/shrVU-8 14.4ns ± 1% 12.3ns ± 2% -14.79% (p=0.000 n=28+29) NonZeroShifts/10/shlVU-8 14.1ns ± 1% 11.9ns ± 2% -15.55% (p=0.000 n=28+27) NonZeroShifts/100/shrVU-8 118ns ± 1% 96ns ± 3% -18.82% (p=0.000 n=30+29) NonZeroShifts/100/shlVU-8 120ns ± 2% 98ns ± 2% -18.46% (p=0.000 n=29+28) NonZeroShifts/1000/shrVU-8 1.10µs ± 1% 0.88µs ± 2% -19.63% (p=0.000 n=29+30) NonZeroShifts/1000/shlVU-8 1.10µs ± 2% 0.88µs ± 2% -20.28% (p=0.000 n=29+28) NonZeroShifts/10000/shrVU-8 10.9µs ± 1% 8.7µs ± 1% -19.78% (p=0.000 n=28+27) NonZeroShifts/10000/shlVU-8 10.9µs ± 2% 8.7µs ± 1% -19.64% (p=0.000 n=29+27) NonZeroShifts/100000/shrVU-8 111µs ± 2% 90µs ± 2% -19.39% (p=0.000 n=28+29) NonZeroShifts/100000/shlVU-8 113µs ± 2% 90µs ± 2% -20.43% (p=0.000 n=30+27) The assembly version is still faster, unfortunately, but the gap is narrowing. Speedup from pure Go to assembly: name old time/op new time/op delta NonZeroShifts/1/shrVU-8 4.39ns ± 1% 3.45ns ± 2% -21.36% (p=0.000 n=27+29) NonZeroShifts/1/shlVU-8 4.10ns ± 2% 3.47ns ± 3% -15.42% (p=0.000 n=28+30) NonZeroShifts/2/shrVU-8 5.63ns ± 2% 3.97ns ± 0% -29.40% (p=0.000 n=29+25) NonZeroShifts/2/shlVU-8 5.14ns ± 1% 3.77ns ± 2% -26.65% (p=0.000 n=28+26) NonZeroShifts/3/shrVU-8 6.35ns ± 2% 4.79ns ± 2% -24.52% (p=0.000 n=29+29) NonZeroShifts/3/shlVU-8 6.25ns ± 1% 4.42ns ± 1% -29.29% (p=0.000 n=27+26) NonZeroShifts/4/shrVU-8 7.06ns ± 2% 5.64ns ± 1% -20.05% (p=0.000 n=30+29) NonZeroShifts/4/shlVU-8 7.24ns ± 1% 5.34ns ± 2% -26.23% (p=0.000 n=29+29) NonZeroShifts/5/shrVU-8 7.93ns ± 1% 6.56ns ± 2% -17.26% (p=0.000 n=26+30) NonZeroShifts/5/shlVU-8 7.92ns ± 1% 6.27ns ± 1% -20.79% (p=0.000 n=29+25) NonZeroShifts/10/shrVU-8 12.3ns ± 2% 10.2ns ± 2% -17.21% (p=0.000 n=29+29) NonZeroShifts/10/shlVU-8 11.9ns ± 2% 10.5ns ± 2% -12.45% (p=0.000 n=27+29) NonZeroShifts/100/shrVU-8 95.9ns ± 3% 77.7ns ± 1% -19.00% (p=0.000 n=29+30) NonZeroShifts/100/shlVU-8 97.5ns ± 2% 66.8ns ± 2% -31.47% (p=0.000 n=28+30) NonZeroShifts/1000/shrVU-8 884ns ± 2% 705ns ± 1% -20.17% (p=0.000 n=30+28) NonZeroShifts/1000/shlVU-8 880ns ± 2% 590ns ± 1% -32.96% (p=0.000 n=28+25) NonZeroShifts/10000/shrVU-8 8.74µs ± 1% 7.34µs ± 3% -15.94% (p=0.000 n=27+30) NonZeroShifts/10000/shlVU-8 8.73µs ± 1% 6.00µs ± 1% -31.25% (p=0.000 n=27+28) NonZeroShifts/100000/shrVU-8 89.6µs ± 2% 75.5µs ± 2% -15.80% (p=0.000 n=29+29) NonZeroShifts/100000/shlVU-8 89.6µs ± 2% 68.0µs ± 3% -24.09% (p=0.000 n=27+30) Change-Id: I18f58d8f5513d737d9cdf09b8f9d14011ffe3958 Reviewed-on: https://go-review.googlesource.com/c/go/+/297050 Trust: Josh Bleecher Snyder <josharian@gmail.com> Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
Paul E. Murphy
|
48ddf70128 |
cmd/asm,cmd/compile: support 5 operand RLWNM/RLWMI on ppc64
These instructions are actually 5 argument opcodes as specified by the ISA. Prior to this patch, the MB and ME arguments were merged into a single bitmask operand to workaround the limitations of the ppc64 assembler backend. This limitation no longer exists. Thus, we can pass operands for these opcodes without having to merge the MB and ME arguments in the assembler frontend or compiler backend. Likewise, support for 4 operand variants is unchanged. Change-Id: Ib086774f3581edeaadfd2190d652aaaa8a90daeb Reviewed-on: https://go-review.googlesource.com/c/go/+/298750 Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Carlos Eduardo Seo <carlos.seo@linaro.org> |
||
|
fanzha02
|
2b50ab2aee |
cmd/compile: optimize single-precision floating point square root
Add generic rule to rewrite the single-precision square root expression with one single-precision instruction. The optimization will reduce two times of precision converting between double-precision and single-precision. On arm64 flatform. previous: FCVTSD F0, F0 FSQRTD F0, F0 FCVTDS F0, F0 optimized: FSQRTS S0, S0 And this patch adds the test case to check the correctness. This patch refers to CL 241877, contributed by Alice Xu (dianhong.xu@arm.com) Change-Id: I6de5d02281c693017ac4bd4c10963dd55989bd7e Reviewed-on: https://go-review.googlesource.com/c/go/+/276873 Trust: fannie zhang <Fannie.Zhang@arm.com> Run-TryBot: fannie zhang <Fannie.Zhang@arm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
Egon Elbre
|
3ee32439b5 |
cmd/compile: ARM64 optimize []float64 and []float32 access
Optimize load and store to []float64 and []float32.
Previously it used LSL instead of shifted register indexed load/store.
Before:
LSL $3, R0, R0
FMOVD F0, (R1)(R0)
After:
FMOVD F0, (R1)(R0<<3)
Fixes #42798
Change-Id: I0c0912140c3dce5aa6abc27097c0eb93833cc589
Reviewed-on: https://go-review.googlesource.com/c/go/+/273706
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Trust: Giovanni Bajo <rasky@develer.com>
|
||
Alejandro García Montoro
|
bf48163e8f |
cmd/compile: add rule to coalesce writes
The code generated when storing eight bytes loaded from memory created a series of small writes instead of a single, large one. The specific pattern of instructions generated stored 1 byte, then 2 bytes, then 4 bytes, and finally 1 byte. The new rules match this specific pattern both for amd64 and for s390x, and convert it into a single instruction to store the 8 bytes. arm64 and ppc64le already generated the right code, but the new codegen test covers also those architectures. Fixes #41663 Change-Id: Ifb9b464be2d59c2ed5034acf7b9c3e473f344030 Reviewed-on: https://go-review.googlesource.com/c/go/+/280456 Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com> Trust: Josh Bleecher Snyder <josharian@gmail.com> Trust: Jason A. Donenfeld <Jason@zx2c4.com> Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> |
||
Keith Randall
|
42cd40ee74 |
cmd/compile: improve bit test code
Some bit test instruction generation stopped triggering after the change to addressing modes. I suspect this was just because ANDQload was being generated before the rewrite rules could discover the BTQ. Fix that by decomposing the ANDQload when it is surrounded by a TESTQ (thus re-enabling the BTQ rules). Fixes #44228 Change-Id: I489b4a5a7eb01c65fc8db0753f8cec54097cadb2 Reviewed-on: https://go-review.googlesource.com/c/go/+/291749 Trust: Keith Randall <khr@golang.org> Trust: Josh Bleecher Snyder <josharian@gmail.com> Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com> |
||
|
Cherry Zhang
|
401d7e5a24 |
[dev.regabi] cmd/compile: reserve X15 as zero register on AMD64
In ABIInternal, reserve X15 as constant zero, and use it to zero memory. (Maybe there can be more use of it?) The register is zeroed when transition to ABIInternal from ABI0. Caveat: using X15 generates longer instructions than using X0. Maybe we want to use X0? Change-Id: I12d5ee92a01fc0b59dad4e5ab023ac71bc2a8b7d Reviewed-on: https://go-review.googlesource.com/c/go/+/288093 Trust: Cherry Zhang <cherryyz@google.com> Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com> |
||
David Chase
|
9a19481acb |
[dev.regabi] cmd/compile: make ordering for InvertFlags more stable
Current many architectures use a rule along the lines of // Canonicalize the order of arguments to comparisons - helps with CSE. ((CMP|CMPW) x y) && x.ID > y.ID => (InvertFlags ((CMP|CMPW) y x)) to normalize comparisons as much as possible for CSE. Replace the ID comparison with something less variable across compiler changes. This helps avoid spurious failures in some of the codegen-comparison tests (though the current choice of comparison is sensitive to Op ordering). Two tests changed to accommodate modified instruction choice. Change-Id: Ib35f450bd2bae9d4f9f7838ceaf7ec682bcf1e1a Reviewed-on: https://go-review.googlesource.com/c/go/+/280155 Trust: David Chase <drchase@google.com> Run-TryBot: David Chase <drchase@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
Lynn Boger
|
0ae3b7cb74 |
cmd/compile: fix rules regression with shifts on PPC64
Some rules for PPC64 were checking for a case where a shift followed by an 'and' of a mask could be lowered, depending on the format of the mask. The function to verify if the mask was valid for this purpose was not checking if the mask was 0 which we don't want to allow. This case can happen if previous optimizations resulted in that mask value. This fixes isPPC64ValidShiftMask to check for a mask of 0 and return false. This also adds a codegen testcase to verify it doesn't try to match the rules in the future. Fixes #42610 Change-Id: I565d94e88495f51321ab365d6388c01e791b4dbb Reviewed-on: https://go-review.googlesource.com/c/go/+/270358 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Paul Murphy <murp@ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.org> Trust: Lynn Boger <laboger@linux.vnet.ibm.com> |
||
Alberto Donizetti
|
7307e86afd |
test/codegen: go fmt
Fixes #42445 Change-Id: I9653ef094dba2a1ac2e3daaa98279d10df17a2a1 Reviewed-on: https://go-review.googlesource.com/c/go/+/268257 Trust: Alberto Donizetti <alb.donizetti@gmail.com> Trust: Martin Möhrmann <moehrmann@google.com> Run-TryBot: Alberto Donizetti <alb.donizetti@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Martin Möhrmann <moehrmann@google.com> |
||
Michael Munday
|
854e892ce1 |
cmd/compile: optimize shift pairs and masks on s390x
Optimize combinations of left and right shifts by a constant value into a 'rotate then insert selected bits [into zero]' instruction. Use the same instruction for contiguous masks since it has some benefits over 'and immediate' (not restricted to 32-bits, does not overwrite source register). To keep the complexity of this change under control I've only implemented 64 bit operations for now. There are a lot more optimizations that can be done with this instruction family. However, since their function overlaps with other instructions we need to be somewhat careful not to break existing optimization rules by creating optimization dead ends. This is particularly true of the load/store merging rules which contain lots of zero extensions and shifts. This CL does interfere with the store merging rules when an operand is shifted left before it is stored: binary.BigEndian.PutUint64(b, x << 1) This is unfortunate but it's not critical and somewhat complex so I plan to fix that in a follow up CL. file before after Δ % addr2line 4117446 4117282 -164 -0.004% api 4945184 4942752 -2432 -0.049% asm 4998079 4991891 -6188 -0.124% buildid 2685158 2684074 -1084 -0.040% cgo 4553732 4553394 -338 -0.007% compile 19294446 19245070 -49376 -0.256% cover 4897105 4891319 -5786 -0.118% dist 3544389 3542785 -1604 -0.045% doc 3926795 3927617 +822 +0.021% fix 3302958 3293868 -9090 -0.275% link 6546274 6543456 -2818 -0.043% nm 4102021 4100825 -1196 -0.029% objdump 4542431 4548483 +6052 +0.133% pack 2482465 2416389 -66076 -2.662% pprof 13366541 13363915 -2626 -0.020% test2json 2829007 2761515 -67492 -2.386% trace 10216164 10219684 +3520 +0.034% vet 6773956 6773572 -384 -0.006% total 107124151 106917891 -206260 -0.193% Change-Id: I7591cce41e06867ba10a745daae9333513062746 Reviewed-on: https://go-review.googlesource.com/c/go/+/233317 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> Trust: Michael Munday <mike.munday@ibm.com> |
||
|
Cherry Zhang
|
0387bedadf |
cmd/compile: remove racefuncenterfp when it is not needed
We already remove racefuncenter and racefuncexit if they are not needed (i.e. the function doesn't have any other race calls). racefuncenterfp is like racefuncenter but used on LR machines. Remove unnecessary racefuncenterfp as well. Change-Id: I65edb00e19c6d9ab55a204cbbb93e9fb710559f1 Reviewed-on: https://go-review.googlesource.com/c/go/+/267099 Trust: Cherry Zhang <cherryyz@google.com> Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: David Chase <drchase@google.com> |
||
|
Paul E. Murphy
|
c3c6fbf314 |
cmd/compile: combine more 32 bit shift and mask operations on ppc64
Combine (AND m (SRWconst x)) or (SRWconst (AND m x)) when mask m is and the shift value produce constant which can be encoded into an RLWINM instruction. Combine (CLRLSLDI (SRWconst x)) if the combining of the underling rotate masks produces a constant which can be encoded into RLWINM. Likewise for (SLDconst (SRWconst x)) and (CLRLSDI (RLWINM x)). Combine rotate word + and operations which can be encoded as a single RLWINM/RLWNM instruction. The most notable performance improvements arise from the crypto benchmarks below (GOARCH=power8 on a ppc64le/linux): pkg:golang.org/x/crypto/blowfish goos:linux goarch:ppc64le ExpandKeyWithSalt 52.2µs ± 0% 47.5µs ± 0% -8.88% ExpandKey 44.4µs ± 0% 40.3µs ± 0% -9.15% pkg:golang.org/x/crypto/ssh/internal/bcrypt_pbkdf goos:linux goarch:ppc64le Key 57.6ms ± 0% 52.3ms ± 0% -9.13% pkg:golang.org/x/crypto/bcrypt goos:linux goarch:ppc64le Equal 90.9ms ± 0% 82.6ms ± 0% -9.13% DefaultCost 91.0ms ± 0% 82.7ms ± 0% -9.12% Change-Id: I59a0ca29face38f4ab46e37124c32906f216c4ce Reviewed-on: https://go-review.googlesource.com/c/go/+/260798 Run-TryBot: Carlos Eduardo Seo <carlos.seo@linaro.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@linaro.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com> |
||
|
Keith Randall
|
04b8a9fea5 |
all: implement GO386=softfloat
Backstop support for non-sse2 chips now that 387 is gone. RELNOTE=yes Change-Id: Ib10e69c4a3654c15a03568f93393437e1939e013 Reviewed-on: https://go-review.googlesource.com/c/go/+/260017 Trust: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Ian Lance Taylor <iant@golang.org> |
||
|
Keith Randall
|
fe2cfb74ba |
all: drop 387 support
My last 387 CL. So sad ... ... ... ... not! Fixes #40255 Change-Id: I8d4ddb744b234b8adc735db2f7c3c7b6d8bbdfa4 Reviewed-on: https://go-review.googlesource.com/c/go/+/258957 Trust: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
|
Lynn Boger
|
cc2a5cf4b8 |
cmd/compile,cmd/internal/obj/ppc64: fix some shift rules due to a regression
A recent change to improve shifts was generating some invalid cases when the rule was based on an AND. The extended mnemonics CLRLSLDI and CLRLSLWI only allow certain values for the operands and in the mask case those values were not being checked properly. This adds a check to those rules to verify that the 'b' and 'n' values used when an AND was part of the rule have correct values. There was a bug in some diag messages in asm9. The message expected 3 values but only provided 2. Those are corrected here also. The test/codegen/shift.go was updated to add a few more cases to check for the case mentioned here. Some of the comments that mention the order of operands in these extended mnemonics were wrong and those have been corrected. Fixes #41683. Change-Id: If5bb860acaa5051b9e0cd80784b2868b85898c31 Reviewed-on: https://go-review.googlesource.com/c/go/+/258138 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> Reviewed-by: Paul Murphy <murp@ibm.com> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> TryBot-Result: Go Bot <gobot@golang.org> Trust: Lynn Boger <laboger@linux.vnet.ibm.com> |
||
|
Lynn Boger
|
a424f6e45e |
cmd/asm,cmd/compile,cmd/internal/obj/ppc64: add extswsli support on power9
This adds support for the extswsli instruction which combines extsw followed by a shift. New benchmark demonstrates the improvement: name old time/op new time/op delta ExtShift 1.34µs ± 0% 1.30µs ± 0% -3.15% (p=0.057 n=4+3) Change-Id: I21b410676fdf15d20e0cbbaa75d7c6dcd3bbb7b0 Reviewed-on: https://go-review.googlesource.com/c/go/+/257017 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Go Bot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <carlos.seo@gmail.com> Trust: Lynn Boger <laboger@linux.vnet.ibm.com> |
||
|
Lynn Boger
|
967465da29 |
cmd/compile: use combined shifts to improve array addressing on ppc64x
This change adds rules to find pairs of instructions that can
be combined into a single shifts. These instruction sequences
are common in array addressing within loops. Improvements can
be seen in many crypto packages and the hash packages.
These are based on the extended mnemonics found in the ISA
sections C.8.1 and C.8.2.
Some rules in PPC64.rules were moved because the ordering prevented
some matching.
The following results were generated on power9.
hash/crc32:
CRC32/poly=Koopman/size=40/align=0 195ns ± 0% 163ns ± 0% -16.41%
CRC32/poly=Koopman/size=40/align=1 200ns ± 0% 163ns ± 0% -18.50%
CRC32/poly=Koopman/size=512/align=0 1.98µs ± 0% 1.67µs ± 0% -15.46%
CRC32/poly=Koopman/size=512/align=1 1.98µs ± 0% 1.69µs ± 0% -14.80%
CRC32/poly=Koopman/size=1kB/align=0 3.90µs ± 0% 3.31µs ± 0% -15.27%
CRC32/poly=Koopman/size=1kB/align=1 3.85µs ± 0% 3.31µs ± 0% -14.15%
CRC32/poly=Koopman/size=4kB/align=0 15.3µs ± 0% 13.1µs ± 0% -14.22%
CRC32/poly=Koopman/size=4kB/align=1 15.4µs ± 0% 13.1µs ± 0% -14.79%
CRC32/poly=Koopman/size=32kB/align=0 137µs ± 0% 105µs ± 0% -23.56%
CRC32/poly=Koopman/size=32kB/align=1 137µs ± 0% 105µs ± 0% -23.53%
crypto/rc4:
RC4_128 733ns ± 0% 650ns ± 0% -11.32% (p=1.000 n=1+1)
RC4_1K 5.80µs ± 0% 5.17µs ± 0% -10.89% (p=1.000 n=1+1)
RC4_8K 45.7µs ± 0% 40.8µs ± 0% -10.73% (p=1.000 n=1+1)
crypto/sha1:
Hash8Bytes 635ns ± 0% 613ns ± 0% -3.46% (p=1.000 n=1+1)
Hash320Bytes 2.30µs ± 0% 2.18µs ± 0% -5.38% (p=1.000 n=1+1)
Hash1K 5.88µs ± 0% 5.38µs ± 0% -8.62% (p=1.000 n=1+1)
Hash8K 42.0µs ± 0% 37.9µs ± 0% -9.75% (p=1.000 n=1+1)
There are other improvements found in golang.org/x/crypto which are all in the
range of 5-15%.
Change-Id: I193471fbcf674151ffe2edab212799d9b08dfb8c
Reviewed-on: https://go-review.googlesource.com/c/go/+/252097
Trust: Lynn Boger <laboger@linux.vnet.ibm.com>
Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com>
|
||
Cuong Manh Le
|
27a30186ab |
cmd/compile,runtime: skip zero'ing order array for select statements
The order array was zero initialized by the compiler, but ends up being overwritten by the runtime anyway. So let the runtime takes full responsibility for initializing, save us one instruction per select. Fixes #40399 Change-Id: Iec1eca27ad7180d4fcb3cc9ef97348206b7fe6b8 Reviewed-on: https://go-review.googlesource.com/c/go/+/251517 Run-TryBot: Cuong Manh Le <cuong.manhle.vn@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Matthew Dempsky <mdempsky@google.com> |
||
|
Paul E. Murphy
|
7615b20d06 |
cmd/compile: generate subfic on ppc64
This merges an lis + subf into subfic, and for 32b constants lwa + subf into oris + ori + subf. The carry bit is no longer used in code generation, therefore I think we can clobber it as needed. Note, lowered borrow/carry arithmetic is self-contained and thus is not affected. A few extra rules are added to ensure early transformations to SUBFCconst don't trip up earlier rules, fold constant operations, or otherwise simplify lowering. Likewise, tests are added to ensure all rules are hit. Generic constant folding catches trivial cases, however some lowering rules insert arithmetic which can introduce new opportunities (e.g BitLen or Slicemask). I couldn't find a specific benchmark to demonstrate noteworthy improvements, but this is generating subfic in many of the default bent test binaries, so we are at least saving a little code space. Change-Id: Iad7c6e5767eaa9dc24dc1c989bd1c8cfe1982012 Reviewed-on: https://go-review.googlesource.com/c/go/+/249461 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Carlos Eduardo Seo <cseo@linux.vnet.ibm.com> |
||
|
fanzha02
|
d556c251a1 |
cmd/compile: add more generic rewrite rules to reassociate (op (op y C) x|C)
With this patch, opt pass can expose more obvious constant-folding
opportunites.
Example:
func test(i int) int {return (i+8)-(i+4)}
The previous version:
MOVD "".i(FP), R0
ADD $8, R0, R1
ADD $4, R0, R0
SUB R0, R1, R0
MOVD R0, "".~r1+8(FP)
RET (R30)
The optimized version:
MOVD $4, R0
MOVD R0, "".~r1+8(FP)
RET (R30)
This patch removes some existing reassociation rules, such as "x+(z-C)",
because the current generic rewrite rules will canonicalize "x-const"
to "x+(-const)", making "x+(z-C)" equal to "x+(z+(-C))".
This patch also adds test cases.
Change-Id: I857108ba0b5fcc18a879eeab38e2551bc4277797
Reviewed-on: https://go-review.googlesource.com/c/go/+/237137
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
|
||
Agniva De Sarker
|
8acbe4c0b3 |
cmd/compile: optimize unsigned comparisons with 0/1 on wasm
Updates #21439 Change-Id: I0fbcde6e0c2fc368fe686b271670f9d8be4a7900 Reviewed-on: https://go-review.googlesource.com/c/go/+/247557 Run-TryBot: Agniva De Sarker <agniva.quicksilver@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Richard Musiol <neelance@gmail.com> |
||
diaxu01
|
01aad9ea93 |
cmd/compile: Optimize ARM64's code with EON
This patch fuses pattern '(MVN (XOR x y))' into '(EON x y)'. Change-Id: I269c98ce198d51a4945ce8bd0e1024acbd1b7609 Reviewed-on: https://go-review.googlesource.com/c/go/+/239638 Run-TryBot: Cherry Zhang <cherryyz@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
|
Paul E. Murphy
|
e7c7ce646f |
cmd/compile: combine multiply/add into maddld on ppc64le/power9
Add a new lowering rule to match and replace such instances with the MADDLD instruction available on power9 where possible. Likewise, this plumbs in a new ppc64 ssa opcode to house the newly generated MADDLD instructions. When testing ed25519, this reduced binary size by 936B. Similarly, MADDLD combination occcurs in a few other less obvious cases such as division by constant. Testing of golang.org/x/crypto/ed25519 shows non-trivial speedup during keygeneration: name old time/op new time/op delta KeyGeneration 65.2µs ± 0% 63.1µs ± 0% -3.19% Signing 64.3µs ± 0% 64.4µs ± 0% +0.16% Verification 147µs ± 0% 147µs ± 0% +0.11% Similarly, this test binary has shrunk by 66488B. Change-Id: I077aeda7943119b41f07e4e62e44a648f16e4ad0 Reviewed-on: https://go-review.googlesource.com/c/go/+/248723 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com> |
||
|
Michael Munday
|
6e876f1985 |
cmd/compile: clean up and optimize s390x multiplication rules
Some of the existing optimizations aren't triggered because they are handled by the generic rules so this CL removes them. Also some constraints were copied without much thought from the amd64 rules and they don't make sense on s390x, so we remove those constraints. Finally, add a 'multiply by the sum of two powers of two' optimization. This makes sense on s390x as shifts are low latency and can also sometimes be optimized further (especially if we add support for RISBG instructions). name old time/op new time/op delta IntMulByConst/3-8 1.70ns ±11% 1.10ns ± 5% -35.26% (p=0.000 n=10+10) IntMulByConst/5-8 1.64ns ± 7% 1.10ns ± 4% -32.94% (p=0.000 n=10+9) IntMulByConst/12-8 1.65ns ± 6% 1.20ns ± 4% -27.16% (p=0.000 n=10+9) IntMulByConst/120-8 1.66ns ± 4% 1.22ns ±13% -26.43% (p=0.000 n=10+10) IntMulByConst/-120-8 1.65ns ± 7% 1.19ns ± 4% -28.06% (p=0.000 n=9+10) IntMulByConst/65537-8 0.86ns ± 9% 1.12ns ±12% +30.41% (p=0.000 n=10+10) IntMulByConst/65538-8 1.65ns ± 5% 1.23ns ± 5% -25.11% (p=0.000 n=10+10) Change-Id: Ib196e6bff1e97febfd266134d0a2b2a62897989f Reviewed-on: https://go-review.googlesource.com/c/go/+/248937 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
Junchen Li
|
06337823ef |
cmd/compile: optimize unsigned comparisons to 0/1 on arm64
For an unsigned integer, it's useful to convert its order test with 0/1
to its equality test with 0. We can save a comparison instruction that
followed by a conditional branch on arm64 since it supports
compare-with-zero-and-branch instructions. For example,
if x > 0 { ... } else { ... }
the original version:
CMP $0, R0
BLS 9
the optimized version:
CBZ R0, 8
Updates #21439
Change-Id: Id1de6f865f6aa72c5d45b29f7894818857288425
Reviewed-on: https://go-review.googlesource.com/c/go/+/246857
Reviewed-by: Keith Randall <khr@golang.org>
|
||
|
Keith Randall
|
ef9c8a38ad |
cmd/compile: don't rewrite (CMP (AND x y) 0) to TEST if AND has other uses
If the AND has other uses, we end up saving an argument to the AND in another register, so we can use it for the TEST. No point in doing that. Change-Id: I73444a6aeddd6f55e2328ce04d77c3e6cf4a83e0 Reviewed-on: https://go-review.googlesource.com/c/go/+/241280 Run-TryBot: Keith Randall <khr@golang.org> Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> |
||
|
Junchen Li
|
e30fbe3757 |
cmd/compile: optimize unsigned comparisons to 0
There are some architecture-independent rules in #21439, since an unsigned integer >= 0 is always true and < 0 is always false. This CL adds these optimizations to generic rules. Updates #21439 Change-Id: Iec7e3040b761ecb1e60908f764815fdd9bc62495 Reviewed-on: https://go-review.googlesource.com/c/go/+/246617 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> |
||
|
Keith Randall
|
c4fed25553 |
cmd/compile: add floating point load+op operations to addressing modes pass
They were missed as part of the refactoring to use a separate addressing modes pass. Fixes #40426 Change-Id: Ie0418b2fac4ba1ffe720644ac918f6d728d5e420 Reviewed-on: https://go-review.googlesource.com/c/go/+/244859 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
Xiangdong Ji
|
e031318ca6 |
cmd/compile: ARM comparisons with 0 incorrect on overflow
Some ARM rewriting rules convert 'comparing to zero' conditions of if statements to a simplified version utilizing CMN and CMP instructions to branch over condition flags, in order to save one Add or Sub caculation. Such optimizations lead to wrong branching in case an overflow/underflow occurs when executing CMN or CMP. Fix the issue by introducing new block opcodes that don't honor the overflow/underflow flag: Block-Op Meaning ARM condition codes 1. LTnoov less than MI 2. GEnoov greater than or equal PL 3. LEnoov less than or equal MI || EQ 4. GTnoov greater than NEQ & PL The patch also adds a few test cases to cover scenarios that are specific to ARM and fine-tunes the code generation tests for 'x-const'. For more details please refer to the previous fix on 64-bit ARM: https://go-review.googlesource.com/c/go/+/233097 Go1 perf, 'old' is the non-optimized version, that is removing all concerned rewriting rules. name old time/op new time/op delta BinaryTree17-8 7.73s ± 0% 7.81s ± 0% +0.97% (p=0.000 n=7+8) Fannkuch11-8 7.06s ± 0% 7.00s ± 0% -0.83% (p=0.000 n=8+8) FmtFprintfEmpty-8 181ns ± 1% 183ns ± 1% +1.31% (p=0.001 n=8+8) FmtFprintfString-8 319ns ± 1% 325ns ± 2% +1.71% (p=0.009 n=7+8) FmtFprintfInt-8 358ns ± 1% 359ns ± 1% ~ (p=0.293 n=7+7) FmtFprintfIntInt-8 459ns ± 3% 456ns ± 1% ~ (p=0.869 n=8+8) FmtFprintfPrefixedInt-8 535ns ± 4% 538ns ± 4% ~ (p=0.572 n=8+8) FmtFprintfFloat-8 1.01µs ± 2% 1.01µs ± 2% ~ (p=0.625 n=8+8) FmtManyArgs-8 1.93µs ± 2% 1.93µs ± 1% ~ (p=0.979 n=8+7) GobDecode-8 16.1ms ± 1% 16.5ms ± 1% +2.32% (p=0.000 n=8+8) GobEncode-8 15.9ms ± 0% 15.8ms ± 1% -1.00% (p=0.000 n=8+7) Gzip-8 690ms ± 1% 670ms ± 0% -2.90% (p=0.000 n=8+8) Gunzip-8 109ms ± 1% 109ms ± 1% ~ (p=0.694 n=7+8) HTTPClientServer-8 149µs ± 3% 146µs ± 2% -1.70% (p=0.028 n=8+8) JSONEncode-8 50.5ms ± 1% 49.2ms ± 0% -2.60% (p=0.001 n=7+7) JSONDecode-8 135ms ± 2% 137ms ± 1% ~ (p=0.054 n=8+7) Mandelbrot200-8 951ms ± 0% 952ms ± 0% ~ (p=0.852 n=6+8) GoParse-8 9.47ms ± 1% 9.66ms ± 1% +2.01% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 288ns ± 2% 277ns ± 2% -3.61% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 1.66µs ± 1% 1.69µs ± 2% +2.21% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 334ns ± 1% 305ns ± 2% -8.86% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 2.14µs ± 2% 2.15µs ± 0% ~ (p=0.099 n=8+8) RegexpMatchMedium_32-8 13.3ns ± 1% 13.3ns ± 0% ~ (p=1.000 n=7+7) RegexpMatchMedium_1K-8 81.1µs ± 3% 80.7µs ± 1% ~ (p=0.955 n=7+8) RegexpMatchHard_32-8 4.26µs ± 0% 4.26µs ± 0% ~ (p=0.933 n=7+8) RegexpMatchHard_1K-8 124µs ± 0% 124µs ± 0% +0.31% (p=0.000 n=8+8) Revcomp-8 14.7ms ± 2% 14.5ms ± 1% -1.66% (p=0.003 n=8+8) Template-8 197ms ± 2% 200ms ± 3% +1.62% (p=0.021 n=8+8) TimeParse-8 1.33µs ± 1% 1.30µs ± 1% -1.86% (p=0.002 n=8+8) TimeFormat-8 3.04µs ± 1% 3.02µs ± 0% -0.60% (p=0.000 n=8+8) name old speed new speed delta GobDecode-8 47.6MB/s ± 1% 46.5MB/s ± 1% -2.28% (p=0.000 n=8+8) GobEncode-8 48.1MB/s ± 0% 48.6MB/s ± 1% +1.02% (p=0.000 n=8+7) Gzip-8 28.1MB/s ± 1% 29.0MB/s ± 0% +2.97% (p=0.000 n=8+8) Gunzip-8 178MB/s ± 1% 179MB/s ± 2% ~ (p=0.694 n=7+8) JSONEncode-8 38.4MB/s ± 1% 39.4MB/s ± 0% +2.67% (p=0.001 n=7+7) JSONDecode-8 14.3MB/s ± 2% 14.2MB/s ± 1% -0.81% (p=0.043 n=8+7) GoParse-8 6.12MB/s ± 1% 5.99MB/s ± 1% -2.00% (p=0.000 n=8+8) RegexpMatchEasy0_32-8 111MB/s ± 2% 115MB/s ± 2% +3.77% (p=0.000 n=8+8) RegexpMatchEasy0_1K-8 618MB/s ± 1% 604MB/s ± 2% -2.16% (p=0.001 n=7+7) RegexpMatchEasy1_32-8 95.7MB/s ± 1% 105.1MB/s ± 2% +9.76% (p=0.000 n=8+8) RegexpMatchEasy1_1K-8 479MB/s ± 2% 477MB/s ± 0% ~ (p=0.105 n=8+8) RegexpMatchMedium_32-8 75.2MB/s ± 1% 75.2MB/s ± 0% ~ (p=0.247 n=7+7) RegexpMatchMedium_1K-8 12.6MB/s ± 3% 12.7MB/s ± 1% ~ (p=0.538 n=7+8) RegexpMatchHard_32-8 7.52MB/s ± 0% 7.52MB/s ± 0% ~ (p=0.968 n=7+8) RegexpMatchHard_1K-8 8.26MB/s ± 0% 8.24MB/s ± 0% -0.30% (p=0.001 n=8+8) Revcomp-8 173MB/s ± 2% 176MB/s ± 1% +1.68% (p=0.003 n=8+8) Template-8 9.85MB/s ± 2% 9.69MB/s ± 3% -1.59% (p=0.021 n=8+8) Fixes #39303 Updates #38740 Change-Id: I0a5f87bfda679f66414c0041ace2ca2e28363f36 Reviewed-on: https://go-review.googlesource.com/c/go/+/236637 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
|
Xiangdong Ji
|
e8f5a33191 |
cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
Block-Op Meaning ARM condition codes
1. LTnoov less than MI
2. GEnoov greater than or equal PL
3. LEnoov less than or equal MI || EQ
4. GTnoov greater than NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
1: 'if x + 3 < 0' might be converted to:
before:
CMN $3, R0
BGE <else branch> // wrong branch is taken if 'x+3' overflows
after:
CMN $3, R0
BPL <else branch>
2: 'if y - 3 > 0' might be converted to:
before:
CMP $3, R0
BLE <else branch> // wrong branch is taken if 'y-3' underflows
after:
CMP $3, R0
BMI <else branch>
BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name old time/op new time/op delta
CondRewrite/SoloJump 13.6ns ± 0% 12.9ns ± 0% -5.15% (p=0.000 n=10+10)
CondRewrite/CombJump 13.8ns ± 1% 12.9ns ± 0% -6.32% (p=0.000 n=10+10)
S2:
name old time/op new time/op delta
CondRewrite/SoloJump 11.6ns ± 0% 10.9ns ± 0% -6.03% (p=0.000 n=10+10)
CondRewrite/CombJump 11.4ns ± 0% 10.8ns ± 1% -5.53% (p=0.000 n=10+10)
S3:
name old time/op new time/op delta
CondRewrite/SoloJump 7.36ns ± 0% 7.50ns ± 0% +1.79% (p=0.000 n=9+10)
CondRewrite/CombJump 7.35ns ± 0% 7.75ns ± 0% +5.51% (p=0.000 n=8+9)
S4:
name old time/op new time/op delta
CondRewrite/SoloJump-224 11.5ns ± 1% 10.9ns ± 0% -4.97% (p=0.000 n=10+10)
CondRewrite/CombJump-224 11.9ns ± 0% 11.5ns ± 0% -2.95% (p=0.000 n=10+10)
S5:
name old time/op new time/op delta
CondRewrite/SoloJump 10.0ns ± 0% 10.0ns ± 0% -0.45% (p=0.000 n=9+10)
CondRewrite/CombJump 9.93ns ± 0% 9.77ns ± 0% -1.53% (p=0.000 n=10+9)
Go1 perf. data:
name old time/op new time/op delta
BinaryTree17 6.29s ± 1% 6.30s ± 1% ~ (p=1.000 n=5+5)
Fannkuch11 5.40s ± 0% 5.40s ± 0% ~ (p=0.841 n=5+5)
FmtFprintfEmpty 97.9ns ± 0% 98.9ns ± 3% ~ (p=0.937 n=4+5)
FmtFprintfString 171ns ± 3% 171ns ± 2% ~ (p=0.754 n=5+5)
FmtFprintfInt 212ns ± 0% 217ns ± 6% +2.55% (p=0.008 n=5+5)
FmtFprintfIntInt 296ns ± 1% 297ns ± 2% ~ (p=0.516 n=5+5)
FmtFprintfPrefixedInt 371ns ± 2% 374ns ± 7% ~ (p=1.000 n=5+5)
FmtFprintfFloat 435ns ± 1% 439ns ± 2% ~ (p=0.056 n=5+5)
FmtManyArgs 1.37µs ± 1% 1.36µs ± 1% ~ (p=0.730 n=5+5)
GobDecode 14.6ms ± 4% 14.4ms ± 4% ~ (p=0.690 n=5+5)
GobEncode 11.8ms ±20% 11.6ms ±15% ~ (p=1.000 n=5+5)
Gzip 507ms ± 0% 491ms ± 0% -3.22% (p=0.008 n=5+5)
Gunzip 73.8ms ± 0% 73.9ms ± 0% ~ (p=0.690 n=5+5)
HTTPClientServer 116µs ± 0% 116µs ± 0% ~ (p=0.686 n=4+4)
JSONEncode 21.8ms ± 1% 21.6ms ± 2% ~ (p=0.151 n=5+5)
JSONDecode 104ms ± 1% 103ms ± 1% -1.08% (p=0.016 n=5+5)
Mandelbrot200 9.53ms ± 0% 9.53ms ± 0% ~ (p=0.421 n=5+5)
GoParse 7.55ms ± 1% 7.51ms ± 1% ~ (p=0.151 n=5+5)
RegexpMatchEasy0_32 158ns ± 0% 158ns ± 0% ~ (all equal)
RegexpMatchEasy0_1K 606ns ± 1% 608ns ± 3% ~ (p=0.937 n=5+5)
RegexpMatchEasy1_32 143ns ± 0% 144ns ± 1% ~ (p=0.095 n=5+4)
RegexpMatchEasy1_1K 927ns ± 2% 944ns ± 2% ~ (p=0.056 n=5+5)
RegexpMatchMedium_32 16.0ns ± 0% 16.0ns ± 0% ~ (all equal)
RegexpMatchMedium_1K 69.3µs ± 2% 69.7µs ± 0% ~ (p=0.690 n=5+5)
RegexpMatchHard_32 3.73µs ± 0% 3.73µs ± 1% ~ (p=0.984 n=5+5)
RegexpMatchHard_1K 111µs ± 1% 110µs ± 0% ~ (p=0.151 n=5+5)
Revcomp 1.91s ±47% 1.77s ±68% ~ (p=1.000 n=5+5)
Template 138ms ± 1% 138ms ± 1% ~ (p=1.000 n=5+5)
TimeParse 787ns ± 2% 785ns ± 1% ~ (p=0.540 n=5+5)
TimeFormat 729ns ± 1% 726ns ± 1% ~ (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
|
||
|
Keith Randall
|
2cb10d42b7 |
cmd/compile: in prove, zero right shifts of positive int by #bits - 1
Taking over Zach's CL 212277. Just cleaned up and added a test.
For a positive, signed integer, an arithmetic right shift of count
(bit-width - 1) equals zero. e.g. int64(22) >> 63 -> 0. This CL makes
prove replace these right shifts with a zero-valued constant.
These shifts may arise in source code explicitly, but can also be
created by the generic rewrite of signed division by a power of 2.
// Signed divide by power of 2.
// n / c = n >> log(c) if n >= 0
// = (n+c-1) >> log(c) if n < 0
// We conditionally add c-1 by adding n>>63>>(64-log(c))
(first shift signed, second shift unsigned).
(Div64 <t> n (Const64 [c])) && isPowerOfTwo(c) ->
(Rsh64x64
(Add64 <t> n (Rsh64Ux64 <t>
(Rsh64x64 <t> n (Const64 <typ.UInt64> [63]))
(Const64 <typ.UInt64> [64-log2(c)])))
(Const64 <typ.UInt64> [log2(c)]))
If n is known to be positive, this rewrite includes an extra Add and 2
extra Rsh. This CL will allow prove to replace one of the extra Rsh with
a 0. That replacement then allows lateopt to remove all the unneccesary
fixups from the generic rewrite.
There is a rewrite rule to handle this case directly:
(Div64 n (Const64 [c])) && isNonNegative(n) && isPowerOfTwo(c) ->
(Rsh64Ux64 n (Const64 <typ.UInt64> [log2(c)]))
But this implementation of isNonNegative really only handles constants
and a few special operations like len/cap. The division could be
handled if the factsTable version of isNonNegative were available.
Unfortunately, the first opt pass happens before prove even has a
chance to deduce the numerator is non-negative, so the generic rewrite
has already fired and created the extra Ops discussed above.
Fixes #36159
By Printf count, this zeroes 137 right shifts when building std and cmd.
Change-Id: Iab486910ac9d7cfb86ace2835456002732b384a2
Reviewed-on: https://go-review.googlesource.com/c/go/+/232857
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
|
||
Martin Möhrmann
|
6ed4661807 |
cmd/compile: optimize make+copy pattern to avoid memclr
match: m = make([]T, x); copy(m, s) for pointer free T and x==len(s) rewrite to: m = mallocgc(x*elemsize(T), nil, false); memmove(&m, &s, x*elemsize(T)) otherwise rewrite to: m = makeslicecopy([]T, x, s) This avoids memclear and shading of pointers in the newly created slice before the copy. With this CL "s" is only be allowed to bev a variable and not a more complex expression. This restriction could be lifted in future versions of this optimization when it can be proven that "s" is not referencing "m". Triggers 450 times during make.bash.. Reduces go binary size by ~8 kbyte. name old time/op new time/op delta MakeSliceCopy/mallocmove/Byte 71.1ns ± 1% 65.8ns ± 0% -7.49% (p=0.000 n=10+9) MakeSliceCopy/mallocmove/Int 71.2ns ± 1% 66.0ns ± 0% -7.27% (p=0.000 n=10+8) MakeSliceCopy/mallocmove/Ptr 104ns ± 4% 99ns ± 1% -5.13% (p=0.000 n=10+10) MakeSliceCopy/makecopy/Byte 70.3ns ± 0% 68.0ns ± 0% -3.22% (p=0.000 n=10+9) MakeSliceCopy/makecopy/Int 70.3ns ± 0% 68.5ns ± 1% -2.59% (p=0.000 n=9+10) MakeSliceCopy/makecopy/Ptr 102ns ± 0% 99ns ± 1% -2.97% (p=0.000 n=9+9) MakeSliceCopy/nilappend/Byte 75.4ns ± 0% 74.9ns ± 2% -0.63% (p=0.015 n=9+9) MakeSliceCopy/nilappend/Int 75.6ns ± 0% 76.4ns ± 3% ~ (p=0.245 n=9+10) MakeSliceCopy/nilappend/Ptr 107ns ± 0% 108ns ± 1% +0.93% (p=0.005 n=9+10) Fixes #26252 Change-Id: Iec553dd1fef6ded16197216a472351c8799a8e71 Reviewed-on: https://go-review.googlesource.com/c/go/+/146719 Reviewed-by: Keith Randall <khr@golang.org> Run-TryBot: Martin Möhrmann <moehrmann@google.com> TryBot-Result: Gobot Gobot <gobot@golang.org> |
||
|
Keith Randall
|
9ed0fb42e3 |
cmd/compile: add indexed memory modification ops to amd64
name old time/op new time/op delta Modify-16 404ns ± 1% 365ns ± 1% -9.73% (p=0.000 n=10+10) ConstModify-16 407ns ± 0% 385ns ± 2% -5.56% (p=0.000 n=9+10) Seems to generally help generated code. Binary size change is in the noise. Change-Id: I57891bfaf0f7dfc5d143bb9f7ebafc7079d2614f Reviewed-on: https://go-review.googlesource.com/c/go/+/228098 Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com> |
||
|
Keith Randall
|
882ec701d2 |
cmd/compile: add indexed load+op operations to amd64
name old time/op new time/op delta LoadAdd-16 545ns ± 0% 456ns ± 0% -16.31% (p=0.000 n=10+10) Update #36468 Change-Id: I84f390d55490648fa1f58cdbc24fd74c4f1bc8c1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227960 Run-TryBot: Keith Randall <khr@golang.org> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com> |
||
|
Josh Bleecher Snyder
|
4a7e363288 |
cmd/compile: optimize Move with all-zero ro sym src to Zero
We set up static symbols during walk that we later make copies of to initialize local variables. It is difficult to ascertain at that time exactly when copying a symbol is profitable vs locally initializing an autotmp. During SSA, we are much better placed to optimize. This change recognizes when we are copying from a global readonly all-zero symbol and replaces it with direct zeroing. This often allows the all-zero symbol to be deadcode eliminated at link time. This is not ideal--it makes for large object files, and longer link times--but it is the cleanest fix I could find. This makes the final binary for the program in #38554 shrink from >500mb to ~2.2mb. It also shrinks the standard binaries: file before after Δ % addr2line 4412496 4404304 -8192 -0.186% buildid 2893816 2889720 -4096 -0.142% cgo 4841048 4832856 -8192 -0.169% compile 19926480 19922432 -4048 -0.020% cover 5281816 5277720 -4096 -0.078% link 6734648 6730552 -4096 -0.061% nm 4366240 4358048 -8192 -0.188% objdump 4755968 4747776 -8192 -0.172% pprof 14653060 14612100 -40960 -0.280% trace 11805940 11777268 -28672 -0.243% vet 7185560 7181416 -4144 -0.058% total 113588440 113465560 -122880 -0.108% And not just by removing unnecessary symbols; the program text shrinks a bit as well. Fixes #38554 Change-Id: I8381ae6084ae145a5e0cd9410c451e52c0dc51c8 Reviewed-on: https://go-review.googlesource.com/c/go/+/229704 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> Reviewed-by: Keith Randall <khr@golang.org> |
||
|
Josh Bleecher Snyder
|
e7c1873691 |
cmd/compile: optimize x & 1 != 0 to x & 1 on amd64
Triggers a handful of times in std+cmd. Change-Id: I9bb8ce9a5f8bae2547cb61157cd8f256e1b63e76 Reviewed-on: https://go-review.googlesource.com/c/go/+/229602 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
|
Michael Munday
|
ab7a65f283 |
cmd/compile: clean up codegen for branch-on-carry on s390x
This CL optimizes code that uses a carry from a function such as
bits.Add64 as the condition in an if statement. For example:
x, c := bits.Add64(a, b, 0)
if c != 0 {
panic("overflow")
}
Rather than converting the carry into a 0 or a 1 value and using
that as an input to a comparison instruction the carry flag is now
used as the input to a conditional branch directly. This typically
removes an ADD LOGICAL WITH CARRY instruction when user code is
doing overflow detection and is closer to the code that a user
would expect to generate.
Change-Id: I950431270955ab72f1b5c6db873b6abe769be0da
Reviewed-on: https://go-review.googlesource.com/c/go/+/219757
Run-TryBot: Michael Munday <mike.munday@ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
|
||
|
Michael Munday
|
e464d7d797 |
cmd/compile: optimize comparisons with immediates on s390x
When generating code for unsigned equals (==) and not equals (!=) comparisons we currently, on s390x, always use signed comparisons. This mostly works well, however signed comparisons on s390x sign extend their immediates and unsigned comparisons zero extend them. For compare-and-branch instructions which can only have 8-bit immediates this significantly changes the range of immediate values we can represent: [-128, 127] for signed comparisons and [0, 255] for unsigned comparisons. When generating equals and not equals checks we don't neet to worry about whether the comparison is signed or unsigned. This CL therefore adds rules to allow us to switch signedness for such comparisons if it means that it brings a constant into range for an 8-bit immediate. For example, a signed equals with an integer in the range [128, 255] will now be implemented using an unsigned compare-and-branch instruction rather than separate compare and branch instructions. As part of this change I've also added support for adding a name to block control values using the same `x:(...)` syntax we use for value rules. Triggers 792 times when compiling cmd and std. Change-Id: I77fa80a128f0a8ce51a2888d1e384bd5e9b61a77 Reviewed-on: https://go-review.googlesource.com/c/go/+/228642 Run-TryBot: Michael Munday <mike.munday@ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Keith Randall <khr@golang.org> |
||
alex-semenyuk
|
876c1feb7d |
test/codegen, runtime/pprof, runtime: apply fmt
Change-Id: Ife4e065246729319c39e57a4fbd8e6f7b37724e1
GitHub-Last-Rev:
|
||
|
Josh Bleecher Snyder
|
50b11318fe |
cmd/compile: use oneBit instead of isPowerOfTwo in bit optimization
This optimization works on any integer with exactly one bit set. This is identical to being a power of two, except in the most negative number. Use oneBit instead. The rule now triggers in a few more places in std+cmd, in packages encoding/asn1, crypto/elliptic, and vendor/golang.org/x/crypto/cryptobyte. This change obviates the need for CL 222479 by doing this optimization consistently in the compiler. Change-Id: I983c6235290fdc634fda5e11b10f1f8ce041272f Reviewed-on: https://go-review.googlesource.com/c/go/+/229124 Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org> |
||
|
David Chase
|
e4e192484b |
cmd/compile: split up the addressing mode on OpAMD64CMP*loadidx* always
Benchmarking suggests that the combo instruction is notably slower, at least in the places where we measure. Updates #37955 Change-Id: I829f1975dd6edf38163128ba51d84604055512f4 Reviewed-on: https://go-review.googlesource.com/c/go/+/228157 Run-TryBot: David Chase <drchase@google.com> Reviewed-by: Keith Randall <khr@golang.org> |
||
|
Lynn Boger
|
a1550d3ca3 |
cmd/compile: use isel with variable shifts on ppc64x
This changes the code generated for variable length shift counts to use isel instead of instructions that set and read the carry flag. This reduces the generated code for shifts like this by 1 instruction and avoids the use of instructions to set and read the carry flag. This sequence can be found in strconv with these results on power9: Atof64Decimal 71.6ns ± 0% 68.3ns ± 0% -4.61% Atof64Float 95.3ns ± 0% 90.9ns ± 0% -4.62% Atof64FloatExp 153ns ± 0% 149ns ± 0% -2.61% Atof64Big 234ns ± 0% 232ns ± 0% -0.85% Atof64RandomBits 348ns ± 0% 369ns ± 0% +6.03% Atof64RandomFloats 262ns ± 0% 262ns ± 0% ~ Atof32Decimal 72.0ns ± 0% 68.2ns ± 0% -5.28% Atof32Float 92.1ns ± 0% 87.1ns ± 0% -5.43% Atof32FloatExp 159ns ± 0% 158ns ± 0% -0.63% Atof32Random 194ns ± 0% 191ns ± 0% -1.55% Some tests in codegen/shift.go are enabled to verify the expected instructions are generated. Change-Id: I968715d10ada405a8c46132bf19b8ed9b85796d1 Reviewed-on: https://go-review.googlesource.com/c/go/+/227337 Run-TryBot: Lynn Boger <laboger@linux.vnet.ibm.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com> |
||
|
Josh Bleecher Snyder
|
ade0811dc8 |
cmd/compile: handle some additional phis in shortcircuit
Prior to this change, the shortcircuit pass could only
handle blocks containing only a single phi control value,
possibly wrapped in some OpNot and OpCopy values.
This change partially lifts this limitation.
It handles some cases in which the block contains other phi values.
This appears to happen most commonly in cases in which
the conditionals being checked involve the memory state,
in which case there is a phi memory value in the block.
The general idea here is to use the information we have about
the CFG to (1) move the other phi values into other blocks
and/or (2) rewrite uses of the other phi values in other blocks.
For example, consider this CFG:
p q
\ /
b
/ \
t u
And consider a phi value v in block b.
We'll write v = Phi(p: x, q: y) to say that v has value x corresponding
to inbound block p, and value y for block q.
We will rewrite this CFG to:
p q
| /
| b
|/ \
t u
What should we do with v?
Any uses of v in u can be replaced with y. Why?
If we are in block u, we came from b, and before that from q.
If prior to b we came from p, then we would have gone to t, not u.
Since we came from q, we know that v took the value y.
Uses of v in t are a bit more complicated.
It is going to end up being a phi value: Phi(p: ?, b: ?).
Suppose, after the rewrite, we came from block p.
Then, before the rewrite, we would have gone to b,
where v would have the value x.
So we have Phi(p: x, b: ?).
Suppose, after the rewrite, we came from block b.
Then we must have come from block q.
If we come from block q, v has value y.
So we have Phi(p: x, b: y).
Uses of v in t can thus be replaced with a new phi value,
with the same values as v, but with altered predecessors.
Similar reasoning can be employed to rewrite or replace
other uses of v elsewhere in the CFG, so that v itself can be eliminated,
and the CFG rewrite can proceed.
This change sets up the infrastructure for such optimizations
and adds a few cheap ones. All optimizations in this change depend
only on the shape of the CFG; future changes may also depend on where
v's uses are. That analysis is more powerful but more expensive,
and should be done incrementally.
The use of closures here is perhaps a bit unusual,
but during development it proved critical to having readable code.
We must decide early on whether we can safely do the CFG modifications,
and then later fix up the phis if so.
Safely storing state and decisions across these two phases is hard to do readably.
Closures solve the problem neatly.
I manually instrumented the code paths in shortcircuitPhiPlan.
During make.bash there are nearly 6000 invocations.
The least-visited code path gets run 85 times,
so all the code in this CL is reasonably well-exercised.
Here is a concrete example of code improved by this change:
func f(e interface{}) int {
if x, ok := e.(int); ok {
return x
}
return 0
}
Omitting PCDATA, FUNCDATA, and the like, it used to compile to:
"".f STEXT nosplit size=50 args=0x18 locals=0x0
0x0000 00000 (x.go:4) LEAQ type.int(SB), AX
0x0007 00007 (x.go:4) MOVQ "".e+8(SP), CX
0x000c 00012 (x.go:4) CMPQ AX, CX
0x000f 00015 (x.go:4) JNE 43
0x0011 00017 (x.go:4) MOVQ "".e+16(SP), AX
0x0016 00022 (x.go:4) MOVQ (AX), AX
0x0019 00025 (x.go:4) JNE 33
0x001b 00027 (x.go:5) MOVQ AX, "".~r1+24(SP)
0x0020 00032 (x.go:5) RET
0x0021 00033 (x.go:7) MOVQ $0, "".~r1+24(SP)
0x002a 00042 (x.go:7) RET
0x002b 00043 (x.go:7) MOVL $0, AX
0x0030 00048 (x.go:4) JMP 25
Afterwards, it compiles to:
"".f STEXT nosplit size=41 args=0x18 locals=0x0
0x0000 00000 (x.go:4) LEAQ type.int(SB), AX
0x0007 00007 (x.go:4) MOVQ "".e+8(SP), CX
0x000c 00012 (x.go:4) CMPQ AX, CX
0x000f 00015 (x.go:4) JNE 31
0x0011 00017 (x.go:4) MOVQ "".e+16(SP), AX
0x0016 00022 (x.go:4) MOVQ (AX), AX
0x0019 00025 (x.go:5) MOVQ AX, "".~r1+24(SP)
0x001e 00030 (x.go:5) RET
0x001f 00031 (x.go:7) MOVQ $0, "".~r1+24(SP)
0x0028 00040 (x.go:7) RET
Note that there is now only a single JNE and a single RET $0 path.
Updates #37608
Has a minor good effect on compilation speed and memory use.
Provides widespread improvements to generated code.
The rare, minor regressions I have investigated are due to
register allocation fluctuations.
file before after Δ %
addr2line 4376080 4371984 -4096 -0.094%
api 5945400 5933112 -12288 -0.207%
asm 5034312 5030216 -4096 -0.081%
buildid 2844952 2840856 -4096 -0.144%
cgo 4812872 4804680 -8192 -0.170%
compile 19622064 19610368 -11696 -0.060%
cover 5236648 5232552 -4096 -0.078%
dist 3658312 3654216 -4096 -0.112%
doc 4653512 4649416 -4096 -0.088%
fix 3370072 3365976 -4096 -0.122%
link 6671864 6667768 -4096 -0.061%
pprof 14781652 14761172 -20480 -0.139%
trace 11639684 11627396 -12288 -0.106%
vet 8252280 8231800 -20480 -0.248%
total 115052984 114934792 -118192 -0.103%
file before after Δ %
internal/cpu.s 3298 3296 -2 -0.061%
internal/bytealg.s 1730 1737 +7 +0.405%
cmd/vendor/golang.org/x/mod/semver.s 7332 7283 -49 -0.668%
image/color.s 8248 8156 -92 -1.115%
math.s 35966 35956 -10 -0.028%
math/cmplx.s 6596 6575 -21 -0.318%
runtime.s 480566 480053 -513 -0.107%
sync.s 16408 16385 -23 -0.140%
math/rand.s 10447 10406 -41 -0.392%
internal/reflectlite.s 28408 28366 -42 -0.148%
errors.s 2736 2701 -35 -1.279%
sort.s 17031 17036 +5 +0.029%
io.s 16993 16964 -29 -0.171%
container/heap.s 2006 1997 -9 -0.449%
text/tabwriter.s 9570 9552 -18 -0.188%
bytes.s 31823 31594 -229 -0.720%
strconv.s 52760 52717 -43 -0.082%
vendor/golang.org/x/text/transform.s 16713 16706 -7 -0.042%
strings.s 42590 42563 -27 -0.063%
bufio.s 22883 22785 -98 -0.428%
encoding/base32.s 9586 9531 -55 -0.574%
syscall.s 82237 82243 +6 +0.007%
image.s 37465 37452 -13 -0.035%
regexp/syntax.s 82827 82769 -58 -0.070%
image/draw.s 18698 18584 -114 -0.610%
image/jpeg.s 36560 36549 -11 -0.030%
time.s 82557 82526 -31 -0.038%
context.s 10863 10820 -43 -0.396%
regexp.s 64114 64049 -65 -0.101%
os.s 51751 51524 -227 -0.439%
reflect.s 168240 168049 -191 -0.114%
cmd/go/internal/lockedfile/internal/filelock.s 2317 2290 -27 -1.165%
path/filepath.s 17831 17766 -65 -0.365%
io/ioutil.s 6994 6990 -4 -0.057%
encoding/binary.s 30791 30726 -65 -0.211%
cmd/vendor/golang.org/x/sys/unix.s 78055 78033 -22 -0.028%
encoding/pem.s 9280 9247 -33 -0.356%
crypto/cipher.s 20376 20374 -2 -0.010%
os/exec.s 29229 29140 -89 -0.304%
internal/goroot.s 4588 4579 -9 -0.196%
cmd/internal/browser.s 2246 2240 -6 -0.267%
cmd/vendor/golang.org/x/crypto/ssh/terminal.s 27183 27149 -34 -0.125%
fmt.s 76625 76484 -141 -0.184%
encoding/hex.s 6154 6152 -2 -0.032%
compress/lzw.s 7063 7059 -4 -0.057%
database/sql/driver.s 18875 18862 -13 -0.069%
debug/plan9obj.s 8268 8266 -2 -0.024%
net/url.s 29724 29719 -5 -0.017%
encoding/csv.s 12872 12856 -16 -0.124%
debug/gosym.s 25303 25268 -35 -0.138%
compress/flate.s 50952 51019 +67 +0.131%
compress/zlib.s 7277 7266 -11 -0.151%
archive/zip.s 42155 42111 -44 -0.104%
debug/dwarf.s 107632 107541 -91 -0.085%
database/sql.s 98373 98028 -345 -0.351%
os/user.s 14722 14708 -14 -0.095%
encoding/json.s 105836 105711 -125 -0.118%
debug/macho.s 32598 32560 -38 -0.117%
encoding/gob.s 136478 135755 -723 -0.530%
debug/pe.s 31160 30869 -291 -0.934%
debug/elf.s 63495 63302 -193 -0.304%
vendor/golang.org/x/text/unicode/bidi.s 27220 27217 -3 -0.011%
vendor/golang.org/x/text/secure/bidirule.s 3363 3352 -11 -0.327%
go/token.s 12036 12035 -1 -0.008%
flag.s 22277 22256 -21 -0.094%
mime.s 39696 39509 -187 -0.471%
go/scanner.s 19033 19020 -13 -0.068%
archive/tar.s 70936 70581 -355 -0.500%
internal/xcoff.s 22823 22820 -3 -0.013%
text/scanner.s 11631 11629 -2 -0.017%
encoding/xml.s 110534 110408 -126 -0.114%
math/big.s 183636 183545 -91 -0.050%
image/gif.s 27376 27343 -33 -0.121%
crypto/dsa.s 6029 5969 -60 -0.995%
image/png.s 42947 42939 -8 -0.019%
crypto/rand.s 6866 6854 -12 -0.175%
vendor/golang.org/x/text/unicode/norm.s 66394 66354 -40 -0.060%
runtime/trace.s 2603 2521 -82 -3.150%
crypto/ed25519.s 6321 6300 -21 -0.332%
text/template/parse.s 93910 93844 -66 -0.070%
crypto/rsa.s 31460 31369 -91 -0.289%
encoding/asn1.s 57021 57023 +2 +0.004%
crypto/elliptic.s 51382 51363 -19 -0.037%
crypto/x509/pkix.s 10386 10342 -44 -0.424%
vendor/golang.org/x/net/idna.s 24482 24466 -16 -0.065%
vendor/golang.org/x/crypto/cryptobyte.s 33479 33280 -199 -0.594%
crypto/ecdsa.s 11936 11883 -53 -0.444%
go/constant.s 43670 42663 -1007 -2.306%
go/ast.s 80383 80191 -192 -0.239%
testing.s 68069 68057 -12 -0.018%
runtime/pprof.s 59613 59603 -10 -0.017%
testing/iotest.s 4895 4891 -4 -0.082%
internal/trace.s 78136 78089 -47 -0.060%
cmd/internal/goobj2.s 13158 13154 -4 -0.030%
cmd/internal/src.s 17661 17657 -4 -0.023%
go/parser.s 79046 78880 -166 -0.210%
cmd/internal/objabi.s 16367 16343 -24 -0.147%
text/template.s 94899 94486 -413 -0.435%
go/printer.s 77267 76992 -275 -0.356%
cmd/internal/goobj.s 25988 25947 -41 -0.158%
runtime/pprof/internal/profile.s 102066 101933 -133 -0.130%
go/format.s 5419 5371 -48 -0.886%
cmd/vendor/golang.org/x/arch/ppc64/ppc64asm.s 37181 37149 -32 -0.086%
go/doc.s 74533 74132 -401 -0.538%
html/template.s 88743 88389 -354 -0.399%
cmd/asm/internal/lex.s 24881 24872 -9 -0.036%
cmd/internal/buildid.s 18263 18256 -7 -0.038%
cmd/vendor/golang.org/x/arch/x86/x86asm.s 80036 79980 -56 -0.070%
go/build.s 68905 68737 -168 -0.244%
cmd/cover.s 46070 45950 -120 -0.260%
cmd/internal/obj.s 117001 116991 -10 -0.009%
cmd/doc.s 62700 62419 -281 -0.448%
cmd/internal/obj/arm.s 66745 66687 -58 -0.087%
cmd/compile/internal/syntax.s 145406 145062 -344 -0.237%
cmd/internal/obj/wasm.s 44049 44027 -22 -0.050%
net.s 291835 291020 -815 -0.279%
cmd/dist.s 209020 208807 -213 -0.102%
cmd/cgo.s 241564 241102 -462 -0.191%
vendor/golang.org/x/net/http/httpproxy.s 9407 9399 -8 -0.085%
log/syslog.s 7921 7909 -12 -0.151%
go/types.s 319325 317513 -1812 -0.567%
vendor/golang.org/x/net/http/httpguts.s 3834 3825 -9 -0.235%
mime/multipart.s 21414 21343 -71 -0.332%
cmd/internal/obj/ppc64.s 119949 119938 -11 -0.009%
cmd/compile/internal/logopt.s 10158 10118 -40 -0.394%
vendor/golang.org/x/net/nettest.s 28012 27991 -21 -0.075%
go/internal/srcimporter.s 6405 6380 -25 -0.390%
go/internal/gcimporter.s 34525 34493 -32 -0.093%
net/mail.s 23937 23720 -217 -0.907%
go/internal/gccgoimporter.s 56095 56038 -57 -0.102%
cmd/compile/internal/types.s 47247 47207 -40 -0.085%
cmd/api.s 39582 39558 -24 -0.061%
cmd/go/internal/base.s 12572 12551 -21 -0.167%
cmd/vendor/golang.org/x/xerrors.s 17846 17814 -32 -0.179%
cmd/vendor/golang.org/x/mod/sumdb/note.s 18142 18070 -72 -0.397%
cmd/go/internal/search.s 19994 19876 -118 -0.590%
cmd/go/internal/imports.s 16457 16428 -29 -0.176%
cmd/vendor/golang.org/x/mod/module.s 17838 17759 -79 -0.443%
cmd/go/internal/cache.s 30551 30514 -37 -0.121%
cmd/vendor/golang.org/x/mod/sumdb/tlog.s 36356 36321 -35 -0.096%
cmd/internal/test2json.s 9452 9408 -44 -0.466%
cmd/go/internal/mvs.s 25136 25092 -44 -0.175%
cmd/go/internal/txtar.s 3488 3461 -27 -0.774%
cmd/vendor/golang.org/x/mod/zip.s 18811 18800 -11 -0.058%
cmd/go/internal/version.s 11213 11171 -42 -0.375%
cmd/link/internal/benchmark.s 4941 4949 +8 +0.162%
cmd/internal/obj/s390x.s 126865 126849 -16 -0.013%
cmd/gofmt.s 30684 30596 -88 -0.287%
cmd/fix.s 87450 86906 -544 -0.622%
cmd/internal/obj/x86.s 88578 88556 -22 -0.025%
cmd/vendor/golang.org/x/mod/modfile.s 72450 72363 -87 -0.120%
cmd/oldlink/internal/loader.s 16743 16741 -2 -0.012%
cmd/pack.s 14863 14861 -2 -0.013%
cmd/go/internal/load.s 106742 106568 -174 -0.163%
cmd/oldlink/internal/objfile.s 21787 21780 -7 -0.032%
cmd/oldlink/internal/loadmacho.s 29309 29317 +8 +0.027%
cmd/oldlink/internal/loadelf.s 35013 35021 +8 +0.023%
cmd/asm/internal/asm.s 68550 68538 -12 -0.018%
cmd/link/internal/loader.s 94765 94564 -201 -0.212%
cmd/link/internal/loadelf.s 35663 35667 +4 +0.011%
cmd/link/internal/loadmacho.s 29501 29509 +8 +0.027%
cmd/vendor/golang.org/x/tools/go/analysis.s 4983 4976 -7 -0.140%
cmd/vendor/golang.org/x/tools/go/analysis/internal/analysisflags.s 16771 16709 -62 -0.370%
cmd/vendor/golang.org/x/tools/go/types/objectpath.s 18481 18456 -25 -0.135%
cmd/vendor/golang.org/x/tools/go/analysis/passes/internal/analysisutil.s 2100 2085 -15 -0.714%
cmd/vendor/github.com/google/pprof/profile.s 150141 149620 -521 -0.347%
cmd/vendor/github.com/google/pprof/internal/measurement.s 10420 10404 -16 -0.154%
cmd/vendor/golang.org/x/tools/go/analysis/passes/asmdecl.s 36814 36755 -59 -0.160%
cmd/vendor/golang.org/x/tools/go/analysis/passes/bools.s 6688 6673 -15 -0.224%
cmd/vendor/golang.org/x/tools/go/analysis/passes/cgocall.s 9856 9784 -72 -0.731%
cmd/vendor/golang.org/x/tools/go/analysis/passes/composite.s 3011 2979 -32 -1.063%
cmd/vendor/golang.org/x/tools/go/analysis/passes/copylock.s 9737 9682 -55 -0.565%
cmd/vendor/golang.org/x/tools/go/cfg.s 30738 30725 -13 -0.042%
cmd/vendor/github.com/ianlancetaylor/demangle.s 175195 174513 -682 -0.389%
cmd/vendor/golang.org/x/tools/go/analysis/passes/httpresponse.s 3625 3520 -105 -2.897%
cmd/vendor/golang.org/x/tools/go/analysis/passes/loopclosure.s 2987 2971 -16 -0.536%
cmd/vendor/golang.org/x/tools/go/analysis/passes/shift.s 4372 4340 -32 -0.732%
cmd/vendor/golang.org/x/tools/go/analysis/passes/stdmethods.s 8634 8611 -23 -0.266%
cmd/vendor/golang.org/x/tools/go/analysis/passes/tests.s 6189 6164 -25 -0.404%
cmd/vendor/golang.org/x/tools/go/analysis/passes/structtag.s 8089 8073 -16 -0.198%
cmd/vendor/golang.org/x/tools/go/analysis/passes/unsafeptr.s 2208 2177 -31 -1.404%
cmd/vendor/golang.org/x/tools/go/analysis/passes/unreachable.s 8050 8047 -3 -0.037%
cmd/vendor/golang.org/x/tools/go/analysis/passes/unusedresult.s 3665 3629 -36 -0.982%
cmd/vendor/golang.org/x/tools/go/ast/astutil.s 65773 65680 -93 -0.141%
cmd/vendor/golang.org/x/tools/go/analysis/unitchecker.s 13328 13286 -42 -0.315%
cmd/vendor/golang.org/x/tools/go/types/typeutil.s 12263 12162 -101 -0.824%
cmd/vendor/golang.org/x/tools/go/analysis/passes/errorsas.s 1459 1421 -38 -2.605%
cmd/vendor/golang.org/x/tools/go/analysis/passes/ctrlflow.s 5208 5191 -17 -0.326%
cmd/vendor/golang.org/x/tools/go/analysis/passes/unmarshal.s 1801 1782 -19 -1.055%
cmd/vendor/golang.org/x/tools/go/analysis/passes/lostcancel.s 9569 9528 -41 -0.428%
cmd/go/internal/work.s 304928 304756 -172 -0.056%
crypto/x509.s 147340 147139 -201 -0.136%
cmd/vendor/golang.org/x/tools/go/analysis/passes/printf.s 34287 34019 -268 -0.782%
crypto/tls.s 311603 310644 -959 -0.308%
cmd/oldlink/internal/ld.s 533115 532651 -464 -0.087%
cmd/oldlink/internal/wasm.s 16484 16458 -26 -0.158%
cmd/oldlink/internal/x86.s 18832 18830 -2 -0.011%
cmd/link/internal/ld.s 548200 547626 -574 -0.105%
cmd/link/internal/wasm.s 16760 16734 -26 -0.155%
cmd/link/internal/arm64.s 20850 20840 -10 -0.048%
cmd/link/internal/x86.s 17437 17435 -2 -0.011%
net/http.s 556647 555519 -1128 -0.203%
net/http/cookiejar.s 15849 15833 -16 -0.101%
expvar.s 9521 9508 -13 -0.137%
net/http/httptest.s 16471 16452 -19 -0.115%
cmd/vendor/github.com/google/pprof/internal/plugin.s 4266 4264 -2 -0.047%
net/http/cgi.s 23448 23428 -20 -0.085%
cmd/go/internal/web.s 16472 16428 -44 -0.267%
net/http/httputil.s 39672 39670 -2 -0.005%
net/rpc.s 33989 33965 -24 -0.071%
net/http/fcgi.s 19167 19162 -5 -0.026%
cmd/vendor/github.com/google/pprof/internal/symbolz.s 5861 5857 -4 -0.068%
cmd/vendor/github.com/google/pprof/internal/binutils.s 35842 35823 -19 -0.053%
cmd/vendor/github.com/google/pprof/internal/symbolizer.s 11449 11404 -45 -0.393%
cmd/go/internal/get.s 62726 62582 -144 -0.230%
cmd/vendor/github.com/google/pprof/internal/report.s 80032 80022 -10 -0.012%
cmd/go/internal/modfetch/codehost.s 89005 88871 -134 -0.151%
cmd/trace.s 116607 116496 -111 -0.095%
cmd/vendor/github.com/google/pprof/internal/driver.s 143234 143207 -27 -0.019%
cmd/vendor/github.com/google/pprof/driver.s 9000 8998 -2 -0.022%
cmd/go/internal/modfetch.s 126300 125726 -574 -0.454%
cmd/pprof.s 12317 12312 -5 -0.041%
cmd/go/internal/modconv.s 17878 17861 -17 -0.095%
cmd/go/internal/modload.s 150261 149763 -498 -0.331%
cmd/go/internal/clean.s 11122 11091 -31 -0.279%
cmd/go/internal/help.s 6523 6521 -2 -0.031%
cmd/go/internal/generate.s 11627 11614 -13 -0.112%
cmd/go/internal/envcmd.s 22034 21986 -48 -0.218%
cmd/go/internal/modget.s 38478 38398 -80 -0.208%
cmd/go/internal/modcmd.s 46430 46229 -201 -0.433%
cmd/go/internal/test.s 64399 64374 -25 -0.039%
cmd/compile/internal/ssa.s 3615264 3608276 -6988 -0.193%
cmd/compile/internal/gc.s 1538865 1537625 -1240 -0.081%
cmd/compile/internal/amd64.s 33593 33574 -19 -0.057%
cmd/compile/internal/x86.s 30871 30852 -19 -0.062%
total 19343565 19311284 -32281 -0.167%
Change-Id: Ib030eb79458827a5a5b6d0d2f98765f8325a4d7e
Reviewed-on: https://go-review.googlesource.com/c/go/+/222923
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
|