diff options
| author | Matthew Dempsky <mdempsky@google.com> | 2021-03-11 15:45:52 -0800 |
|---|---|---|
| committer | Matthew Dempsky <mdempsky@google.com> | 2021-03-12 18:02:59 +0000 |
| commit | 4662029264e79f144eef4323631b3356624e884f (patch) | |
| tree | b59453243f0f51d85d840a3677bd33a1625a2e18 /src/runtime/sizeclasses.go | |
| parent | 735647d92e839f9ac3a91864a2c34263338a35e6 (diff) | |
| download | go-git-4662029264e79f144eef4323631b3356624e884f.tar.gz | |
runtime: simplify divmagic for span calculations
It's both simpler and faster to just unconditionally do two 32-bit
multiplies rather than a bunch of branching to try to avoid them.
This is safe thanks to the tight bounds derived in [1] and verified
during mksizeclasses.go.
Benchstat results below for compilebench benchmarks on my P920. See
also [2] for micro benchmarks comparing the new functions against the
originals (as well as several basic attempts at optimizing them).
name old time/op new time/op delta
Template 295ms ± 3% 290ms ± 1% -1.95% (p=0.000 n=20+20)
Unicode 113ms ± 3% 110ms ± 2% -2.32% (p=0.000 n=21+17)
GoTypes 1.78s ± 1% 1.76s ± 1% -1.23% (p=0.000 n=21+20)
Compiler 119ms ± 2% 117ms ± 4% -1.53% (p=0.007 n=20+20)
SSA 14.3s ± 1% 13.8s ± 1% -3.12% (p=0.000 n=17+20)
Flate 173ms ± 2% 170ms ± 1% -1.64% (p=0.000 n=20+19)
GoParser 278ms ± 2% 273ms ± 2% -1.92% (p=0.000 n=20+19)
Reflect 686ms ± 3% 671ms ± 3% -2.18% (p=0.000 n=19+20)
Tar 255ms ± 2% 248ms ± 2% -2.90% (p=0.000 n=20+20)
XML 335ms ± 3% 327ms ± 2% -2.34% (p=0.000 n=20+20)
LinkCompiler 799ms ± 1% 799ms ± 1% ~ (p=0.925 n=20+20)
ExternalLinkCompiler 1.90s ± 1% 1.90s ± 0% ~ (p=0.327 n=20+20)
LinkWithoutDebugCompiler 385ms ± 1% 386ms ± 1% ~ (p=0.251 n=18+20)
[Geo mean] 512ms 504ms -1.61%
name old user-time/op new user-time/op delta
Template 286ms ± 4% 282ms ± 4% -1.42% (p=0.025 n=21+20)
Unicode 104ms ± 9% 102ms ±14% ~ (p=0.294 n=21+20)
GoTypes 1.75s ± 3% 1.72s ± 2% -1.36% (p=0.000 n=21+20)
Compiler 109ms ±11% 108ms ± 8% ~ (p=0.187 n=21+19)
SSA 14.0s ± 1% 13.5s ± 2% -3.25% (p=0.000 n=16+20)
Flate 166ms ± 4% 164ms ± 4% -1.34% (p=0.032 n=19+19)
GoParser 268ms ± 4% 263ms ± 4% -1.71% (p=0.011 n=18+20)
Reflect 666ms ± 3% 654ms ± 4% -1.77% (p=0.002 n=18+20)
Tar 245ms ± 5% 236ms ± 6% -3.34% (p=0.000 n=20+20)
XML 320ms ± 4% 314ms ± 3% -2.01% (p=0.001 n=19+18)
LinkCompiler 744ms ± 4% 747ms ± 3% ~ (p=0.627 n=20+19)
ExternalLinkCompiler 1.71s ± 3% 1.72s ± 2% ~ (p=0.149 n=20+20)
LinkWithoutDebugCompiler 345ms ± 6% 342ms ± 8% ~ (p=0.355 n=20+20)
[Geo mean] 484ms 477ms -1.50%
[1] Daniel Lemire, Owen Kaser, Nathan Kurz. 2019. "Faster Remainder by
Direct Computation: Applications to Compilers and Software Libraries."
https://arxiv.org/abs/1902.01961
[2] https://github.com/mdempsky/benchdivmagic
Change-Id: Ie4d214e7a908b0d979c878f2d404bd56bdf374f6
Reviewed-on: https://go-review.googlesource.com/c/go/+/300994
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Trust: Matthew Dempsky <mdempsky@google.com>
Trust: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Michael Knyszek <mknyszek@google.com>
Diffstat (limited to 'src/runtime/sizeclasses.go')
| -rw-r--r-- | src/runtime/sizeclasses.go | 10 |
1 files changed, 1 insertions, 9 deletions
diff --git a/src/runtime/sizeclasses.go b/src/runtime/sizeclasses.go index d71ceeab7b..65c72cfb1a 100644 --- a/src/runtime/sizeclasses.go +++ b/src/runtime/sizeclasses.go @@ -92,14 +92,6 @@ const ( var class_to_size = [_NumSizeClasses]uint16{0, 8, 16, 24, 32, 48, 64, 80, 96, 112, 128, 144, 160, 176, 192, 208, 224, 240, 256, 288, 320, 352, 384, 416, 448, 480, 512, 576, 640, 704, 768, 896, 1024, 1152, 1280, 1408, 1536, 1792, 2048, 2304, 2688, 3072, 3200, 3456, 4096, 4864, 5376, 6144, 6528, 6784, 6912, 8192, 9472, 9728, 10240, 10880, 12288, 13568, 14336, 16384, 18432, 19072, 20480, 21760, 24576, 27264, 28672, 32768} var class_to_allocnpages = [_NumSizeClasses]uint8{0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 2, 1, 2, 1, 3, 2, 3, 1, 3, 2, 3, 4, 5, 6, 1, 7, 6, 5, 4, 3, 5, 7, 2, 9, 7, 5, 8, 3, 10, 7, 4} - -type divMagic struct { - shift uint8 - shift2 uint8 - mul uint16 - baseMask uint16 -} - -var class_to_divmagic = [_NumSizeClasses]divMagic{{0, 0, 0, 0}, {3, 0, 1, 65528}, {4, 0, 1, 65520}, {3, 11, 683, 0}, {5, 0, 1, 65504}, {4, 11, 683, 0}, {6, 0, 1, 65472}, {4, 10, 205, 0}, {5, 9, 171, 0}, {4, 11, 293, 0}, {7, 0, 1, 65408}, {4, 13, 911, 0}, {5, 10, 205, 0}, {4, 12, 373, 0}, {6, 9, 171, 0}, {4, 13, 631, 0}, {5, 11, 293, 0}, {4, 13, 547, 0}, {8, 0, 1, 65280}, {5, 9, 57, 0}, {6, 9, 103, 0}, {5, 12, 373, 0}, {7, 7, 43, 0}, {5, 10, 79, 0}, {6, 10, 147, 0}, {5, 11, 137, 0}, {9, 0, 1, 65024}, {6, 9, 57, 0}, {7, 9, 103, 0}, {6, 11, 187, 0}, {8, 7, 43, 0}, {7, 8, 37, 0}, {10, 0, 1, 64512}, {7, 9, 57, 0}, {8, 6, 13, 0}, {7, 11, 187, 0}, {9, 5, 11, 0}, {8, 8, 37, 0}, {11, 0, 1, 63488}, {8, 9, 57, 0}, {7, 10, 49, 0}, {10, 5, 11, 0}, {7, 10, 41, 0}, {7, 9, 19, 0}, {12, 0, 1, 61440}, {8, 9, 27, 0}, {8, 10, 49, 0}, {11, 5, 11, 0}, {7, 13, 161, 0}, {7, 13, 155, 0}, {8, 9, 19, 0}, {13, 0, 1, 57344}, {8, 12, 111, 0}, {9, 9, 27, 0}, {11, 6, 13, 0}, {7, 14, 193, 0}, {12, 3, 3, 0}, {8, 13, 155, 0}, {11, 8, 37, 0}, {14, 0, 1, 49152}, {11, 8, 29, 0}, {7, 13, 55, 0}, {12, 5, 7, 0}, {8, 14, 193, 0}, {13, 3, 3, 0}, {7, 14, 77, 0}, {12, 7, 19, 0}, {15, 0, 1, 32768}} +var class_to_divmagic = [_NumSizeClasses]uint32{0, ^uint32(0)/8 + 1, ^uint32(0)/16 + 1, ^uint32(0)/24 + 1, ^uint32(0)/32 + 1, ^uint32(0)/48 + 1, ^uint32(0)/64 + 1, ^uint32(0)/80 + 1, ^uint32(0)/96 + 1, ^uint32(0)/112 + 1, ^uint32(0)/128 + 1, ^uint32(0)/144 + 1, ^uint32(0)/160 + 1, ^uint32(0)/176 + 1, ^uint32(0)/192 + 1, ^uint32(0)/208 + 1, ^uint32(0)/224 + 1, ^uint32(0)/240 + 1, ^uint32(0)/256 + 1, ^uint32(0)/288 + 1, ^uint32(0)/320 + 1, ^uint32(0)/352 + 1, ^uint32(0)/384 + 1, ^uint32(0)/416 + 1, ^uint32(0)/448 + 1, ^uint32(0)/480 + 1, ^uint32(0)/512 + 1, ^uint32(0)/576 + 1, ^uint32(0)/640 + 1, ^uint32(0)/704 + 1, ^uint32(0)/768 + 1, ^uint32(0)/896 + 1, ^uint32(0)/1024 + 1, ^uint32(0)/1152 + 1, ^uint32(0)/1280 + 1, ^uint32(0)/1408 + 1, ^uint32(0)/1536 + 1, ^uint32(0)/1792 + 1, ^uint32(0)/2048 + 1, ^uint32(0)/2304 + 1, ^uint32(0)/2688 + 1, ^uint32(0)/3072 + 1, ^uint32(0)/3200 + 1, ^uint32(0)/3456 + 1, ^uint32(0)/4096 + 1, ^uint32(0)/4864 + 1, ^uint32(0)/5376 + 1, ^uint32(0)/6144 + 1, ^uint32(0)/6528 + 1, ^uint32(0)/6784 + 1, ^uint32(0)/6912 + 1, ^uint32(0)/8192 + 1, ^uint32(0)/9472 + 1, ^uint32(0)/9728 + 1, ^uint32(0)/10240 + 1, ^uint32(0)/10880 + 1, ^uint32(0)/12288 + 1, ^uint32(0)/13568 + 1, ^uint32(0)/14336 + 1, ^uint32(0)/16384 + 1, ^uint32(0)/18432 + 1, ^uint32(0)/19072 + 1, ^uint32(0)/20480 + 1, ^uint32(0)/21760 + 1, ^uint32(0)/24576 + 1, ^uint32(0)/27264 + 1, ^uint32(0)/28672 + 1, ^uint32(0)/32768 + 1} var size_to_class8 = [smallSizeMax/smallSizeDiv + 1]uint8{0, 1, 2, 3, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 14, 15, 15, 16, 16, 17, 17, 18, 18, 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 22, 22, 22, 22, 23, 23, 23, 23, 24, 24, 24, 24, 25, 25, 25, 25, 26, 26, 26, 26, 27, 27, 27, 27, 27, 27, 27, 27, 28, 28, 28, 28, 28, 28, 28, 28, 29, 29, 29, 29, 29, 29, 29, 29, 30, 30, 30, 30, 30, 30, 30, 30, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32} var size_to_class128 = [(_MaxSmallSize-smallSizeMax)/largeSizeDiv + 1]uint8{32, 33, 34, 35, 36, 37, 37, 38, 38, 39, 39, 40, 40, 40, 41, 41, 41, 42, 43, 43, 44, 44, 44, 44, 44, 45, 45, 45, 45, 45, 45, 46, 46, 46, 46, 47, 47, 47, 47, 47, 47, 48, 48, 48, 49, 49, 50, 51, 51, 51, 51, 51, 51, 51, 51, 51, 51, 52, 52, 52, 52, 52, 52, 52, 52, 52, 52, 53, 53, 54, 54, 54, 54, 55, 55, 55, 55, 55, 56, 56, 56, 56, 56, 56, 56, 56, 56, 56, 56, 57, 57, 57, 57, 57, 57, 57, 57, 57, 57, 58, 58, 58, 58, 58, 58, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 59, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 61, 61, 61, 61, 61, 62, 62, 62, 62, 62, 62, 62, 62, 62, 62, 62, 63, 63, 63, 63, 63, 63, 63, 63, 63, 63, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 65, 66, 66, 66, 66, 66, 66, 66, 66, 66, 66, 66, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67} |