[libc-commits] [libc] [libc][gpu] Add exp/log benchmarks and flexible input generation (PR #155727)
Leandro Lacerda via libc-commits
libc-commits at lists.llvm.org
Wed Aug 27 17:09:19 PDT 2025
leandrolcampos wrote:
Here's what I get on my *NVIDIA GeForce RTX 4070 Laptop GPU*.
**Note the exceptionally low and consistent timings for `__nv_expf` and `__nv_logf`: are they mapped to a hardware-level implementation (likely SFUs)?**
```
[1/10] Running hermetic test libc.benchmarks.gpu.src.ctype.isalnum_benchmark
Running Suite: LlvmLibcIsAlNumGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
IsAlnum | 53 | 0 | 53 | 53 | 11904 | 64 |
IsAlnumSingleThread | 53 | 0 | 53 | 53 | 186 | 1 |
IsAlnumSingleWave | 53 | 0 | 53 | 53 | 5952 | 32 |
IsAlnumCapital | 53 | 0 | 53 | 53 | 11904 | 64 |
IsAlnumNotAlnum | 43 | 0 | 43 | 43 | 11904 | 64 |
[2/10] Running hermetic test libc.benchmarks.gpu.src.ctype.isalpha_benchmark
Running Suite: LlvmLibcIsAlphaGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
IsAlpha | 53 | 0 | 53 | 53 | 186 | 1 |
[3/10] Running hermetic test libc.benchmarks.gpu.src.math.atan2_benchmark
Running Suite: LlvmLibcAtan2GpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
Atan2_1 | 4075 | 951 | 1894 | 5187 | 24032 | 32 |
Atan2_128 | 3852 | 80 | 3531 | 4111 | 131648 | 32 |
Atan2_1024 | 4083 | 31 | 3991 | 4150 | 2880 | 32 |
Atan2_4096 | 4080 | 15 | 4058 | 4110 | 576 | 32 |
Atan2TwoPi_1 | 2738 | 16 | 2727 | 3161 | 24032 | 32 |
Atan2TwoPi_128 | 2511 | 2 | 2508 | 2515 | 352 | 32 |
Atan2TwoPi_1024 | 2743 | 1 | 2742 | 2744 | 352 | 32 |
Atan2TwoPi_4096 | 2745 | 0 | 2745 | 2745 | 352 | 32 |
Atan2TwoPow30_1 | 2734 | 15 | 2723 | 3145 | 24032 | 32 |
Atan2TwoPow30_128 | 2517 | 2 | 2512 | 2525 | 1344 | 32 |
Atan2TwoPow30_1024 | 2743 | 0 | 2743 | 2744 | 352 | 32 |
Atan2TwoPow30_4096 | 2745 | 0 | 2744 | 2745 | 352 | 32 |
Atan2Large_1 | 3570 | 382 | 1125 | 3883 | 131648 | 32 |
Atan2Large_128 | 3352 | 37 | 3280 | 3421 | 1984 | 32 |
Atan2Large_1024 | 3577 | 12 | 3543 | 3605 | 4160 | 32 |
Atan2Large_4096 | 3576 | 6 | 3566 | 3586 | 576 | 32 |
NvAtan2_1 | 2909 | 38 | 2866 | 3341 | 17024 | 32 |
NvAtan2_128 | 2801 | 2 | 2798 | 2805 | 352 | 32 |
NvAtan2_1024 | 3040 | 1 | 3039 | 3041 | 352 | 32 |
NvAtan2_4096 | 3041 | 1 | 3040 | 3042 | 352 | 32 |
NvAtan2TwoPi_1 | 2032 | 13 | 2032 | 2384 | 24032 | 32 |
NvAtan2TwoPi_128 | 1945 | 1 | 1945 | 1947 | 352 | 32 |
NvAtan2TwoPi_1024 | 2184 | 0 | 2184 | 2185 | 576 | 32 |
NvAtan2TwoPi_4096 | 2185 | 0 | 2185 | 2185 | 352 | 32 |
NvAtan2TwoPow30_1 | 2032 | 8 | 2032 | 2184 | 12032 | 32 |
NvAtan2TwoPow30_128 | 1945 | 1 | 1945 | 1951 | 896 | 32 |
NvAtan2TwoPow30_1024 | 2185 | 0 | 2184 | 2185 | 352 | 32 |
NvAtan2TwoPow30_4096 | 2185 | 0 | 2185 | 2185 | 352 | 32 |
NvAtan2Large_1 | 2032 | 12 | 2032 | 2356 | 24032 | 32 |
NvAtan2Large_128 | 1945 | 1 | 1945 | 1951 | 896 | 32 |
NvAtan2Large_1024 | 2184 | 0 | 2184 | 2184 | 352 | 32 |
NvAtan2Large_4096 | 2185 | 0 | 2185 | 2186 | 352 | 32 |
[4/10] Running hermetic test libc.benchmarks.gpu.src.math.exp_benchmark
Running Suite: LlvmLibcExpGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
ExpSubnormal_1 | 172 | 3 | 172 | 431 | 258688 | 32 |
ExpSubnormal_128 | 159 | 0 | 159 | 161 | 1984 | 32 |
ExpSubnormal_1024 | 349 | 0 | 348 | 349 | 896 | 32 |
ExpSubnormal_4096 | 368 | 1 | 367 | 369 | 1344 | 32 |
ExpCoreRange_1 | 972 | 12 | 952 | 1464 | 66880 | 32 |
ExpCoreRange_128 | 765 | 1 | 763 | 767 | 576 | 32 |
ExpCoreRange_1024 | 951 | 0 | 951 | 952 | 352 | 32 |
ExpCoreRange_4096 | 968 | 0 | 968 | 969 | 352 | 32 |
ExpFinite_1 | 1107 | 125 | 953 | 1476 | 12032 | 32 |
ExpFinite_128 | 907 | 11 | 867 | 929 | 2880 | 32 |
ExpFinite_1024 | 1092 | 4 | 1084 | 1102 | 1984 | 32 |
ExpFinite_4096 | 1110 | 2 | 1106 | 1113 | 896 | 32 |
ExpUnderflow_1 | 1513 | 98 | 525 | 1753 | 2735008 | 32 |
ExpUnderflow_128 | 1385 | 7 | 1360 | 1397 | 4160 | 32 |
ExpUnderflow_1024 | 1562 | 3 | 1554 | 1567 | 5952 | 32 |
ExpUnderflow_4096 | 1581 | 2 | 1577 | 1584 | 1344 | 32 |
ExpOverflow_1 | 1425 | 9 | 1405 | 1480 | 2880 | 32 |
ExpOverflow_128 | 1249 | 1 | 1245 | 1251 | 896 | 32 |
ExpOverflow_1024 | 1434 | 0 | 1433 | 1434 | 352 | 32 |
ExpOverflow_4096 | 1453 | 0 | 1453 | 1453 | 352 | 32 |
NvExpSubnormal_1 | 826 | 3 | 826 | 902 | 17024 | 32 |
NvExpSubnormal_128 | 778 | 0 | 778 | 780 | 576 | 32 |
NvExpSubnormal_1024 | 990 | 0 | 990 | 990 | 352 | 32 |
NvExpSubnormal_4096 | 1012 | 0 | 1011 | 1012 | 352 | 32 |
NvExpCoreRange_1 | 826 | 8 | 826 | 1176 | 66880 | 32 |
NvExpCoreRange_128 | 778 | 0 | 778 | 778 | 352 | 32 |
NvExpCoreRange_1024 | 990 | 0 | 990 | 990 | 352 | 32 |
NvExpCoreRange_4096 | 1012 | 0 | 1012 | 1012 | 352 | 32 |
NvExpFinite_1 | 883 | 51 | 826 | 1004 | 362464 | 32 |
NvExpFinite_128 | 835 | 4 | 820 | 847 | 17024 | 32 |
NvExpFinite_1024 | 1048 | 2 | 1044 | 1052 | 1984 | 32 |
NvExpFinite_4096 | 1070 | 1 | 1069 | 1071 | 352 | 32 |
NvExpUnderflow_1 | 911 | 8 | 911 | 1235 | 47616 | 32 |
NvExpUnderflow_128 | 862 | 0 | 862 | 862 | 352 | 32 |
NvExpUnderflow_1024 | 1074 | 0 | 1074 | 1074 | 352 | 32 |
NvExpUnderflow_4096 | 1096 | 0 | 1095 | 1096 | 352 | 32 |
NvExpOverflow_1 | 911 | 4 | 911 | 987 | 12032 | 32 |
NvExpOverflow_128 | 862 | 0 | 862 | 862 | 352 | 32 |
NvExpOverflow_1024 | 1074 | 0 | 1074 | 1075 | 352 | 32 |
NvExpOverflow_4096 | 1096 | 0 | 1095 | 1096 | 352 | 32 |
[5/10] Running hermetic test libc.benchmarks.gpu.src.math.expf_benchmark
Running Suite: LlvmLibcExpfGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
ExpfSubnormal_1 | 179 | 3 | 179 | 437 | 258688 | 32 |
ExpfSubnormal_128 | 129 | 0 | 129 | 131 | 2880 | 32 |
ExpfSubnormal_1024 | 307 | 0 | 304 | 307 | 2880 | 32 |
ExpfSubnormal_4096 | 326 | 0 | 326 | 326 | 352 | 32 |
ExpfCoreRange_1 | 809 | 10 | 799 | 1315 | 93856 | 32 |
ExpfCoreRange_128 | 517 | 1 | 515 | 520 | 896 | 32 |
ExpfCoreRange_1024 | 691 | 0 | 691 | 692 | 1344 | 32 |
ExpfCoreRange_4096 | 709 | 0 | 709 | 709 | 352 | 32 |
ExpfFinite_1 | 898 | 22 | 820 | 1011 | 4160 | 32 |
ExpfFinite_128 | 603 | 2 | 600 | 606 | 352 | 32 |
ExpfFinite_1024 | 776 | 1 | 773 | 777 | 1344 | 32 |
ExpfFinite_4096 | 792 | 0 | 791 | 792 | 352 | 32 |
ExpfUnderflow_1 | 1105 | 189 | 865 | 1404 | 2735008 | 32 |
ExpfUnderflow_128 | 804 | 16 | 744 | 858 | 93856 | 32 |
ExpfUnderflow_1024 | 977 | 6 | 963 | 992 | 2880 | 32 |
ExpfUnderflow_4096 | 996 | 3 | 987 | 1001 | 4160 | 32 |
ExpfOverflow_1 | 804 | 5 | 798 | 958 | 33856 | 32 |
ExpfOverflow_128 | 514 | 1 | 512 | 516 | 896 | 32 |
ExpfOverflow_1024 | 689 | 0 | 689 | 689 | 352 | 32 |
ExpfOverflow_4096 | 706 | 0 | 706 | 706 | 352 | 32 |
NvExpfSubnormal_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvExpfSubnormal_128 | 49 | 0 | 49 | 49 | 576 | 32 |
NvExpfSubnormal_1024 | 258 | 0 | 258 | 258 | 352 | 32 |
NvExpfSubnormal_4096 | 280 | 0 | 280 | 280 | 352 | 32 |
NvExpfCoreRange_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvExpfCoreRange_128 | 49 | 0 | 49 | 49 | 576 | 32 |
NvExpfCoreRange_1024 | 258 | 0 | 258 | 258 | 352 | 32 |
NvExpfCoreRange_4096 | 280 | 0 | 280 | 280 | 352 | 32 |
NvExpfFinite_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvExpfFinite_128 | 49 | 0 | 49 | 49 | 576 | 32 |
NvExpfFinite_1024 | 258 | 0 | 258 | 258 | 352 | 32 |
NvExpfFinite_4096 | 280 | 0 | 280 | 280 | 352 | 32 |
NvExpfUnderflow_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvExpfUnderflow_128 | 49 | 0 | 49 | 49 | 576 | 32 |
NvExpfUnderflow_1024 | 258 | 0 | 258 | 258 | 352 | 32 |
NvExpfUnderflow_4096 | 280 | 0 | 280 | 280 | 352 | 32 |
NvExpfOverflow_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvExpfOverflow_128 | 49 | 0 | 49 | 49 | 576 | 32 |
NvExpfOverflow_1024 | 258 | 0 | 258 | 258 | 352 | 32 |
NvExpfOverflow_4096 | 280 | 0 | 280 | 280 | 352 | 32 |
[6/10] Running hermetic test libc.benchmarks.gpu.src.math.expf16_benchmark
Running Suite: LlvmLibcExpf16GpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
Expf16Subnormal_1 | 306 | 5 | 306 | 610 | 131648 | 32 |
Expf16Subnormal_128 | 231 | 1 | 231 | 246 | 12032 | 32 |
Expf16Subnormal_1024 | 231 | 1 | 231 | 242 | 8480 | 32 |
Expf16Subnormal_4096 | 334 | 0 | 334 | 334 | 352 | 32 |
Expf16CoreRange_1 | 519 | 51 | 499 | 763 | 2735008 | 32 |
Expf16CoreRange_128 | 222 | 4 | 214 | 234 | 1984 | 32 |
Expf16CoreRange_1024 | 220 | 1 | 217 | 225 | 5952 | 32 |
Expf16CoreRange_4096 | 322 | 1 | 320 | 324 | 2880 | 32 |
Expf16Finite_1 | 653 | 29 | 503 | 804 | 4160 | 32 |
Expf16Finite_128 | 351 | 2 | 347 | 356 | 4160 | 32 |
Expf16Finite_1024 | 349 | 1 | 347 | 351 | 1984 | 32 |
Expf16Finite_4096 | 451 | 0 | 451 | 452 | 576 | 32 |
Expf16Underflow_1 | 628 | 5 | 625 | 796 | 47616 | 32 |
Expf16Underflow_128 | 328 | 0 | 328 | 329 | 896 | 32 |
Expf16Underflow_1024 | 326 | 0 | 326 | 328 | 1344 | 32 |
Expf16Underflow_4096 | 429 | 0 | 429 | 429 | 352 | 32 |
Expf16Overflow_1 | 550 | 138 | 497 | 926 | 184576 | 32 |
Expf16Overflow_128 | 254 | 12 | 215 | 301 | 258688 | 32 |
Expf16Overflow_1024 | 252 | 4 | 238 | 266 | 66880 | 32 |
Expf16Overflow_4096 | 356 | 2 | 350 | 360 | 1984 | 32 |
[7/10] Running hermetic test libc.benchmarks.gpu.src.math.log_benchmark
Running Suite: LlvmLibcLogGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
LogSubnormal_1 | 1030 | 8 | 1014 | 1295 | 66880 | 32 |
LogSubnormal_128 | 606 | 2 | 603 | 610 | 1344 | 32 |
LogSubnormal_1024 | 808 | 0 | 808 | 809 | 352 | 32 |
LogSubnormal_4096 | 827 | 0 | 825 | 827 | 1344 | 32 |
LogAroundOne_1 | 1031 | 8 | 1017 | 1082 | 1984 | 32 |
LogAroundOne_128 | 608 | 2 | 604 | 615 | 1984 | 32 |
LogAroundOne_1024 | 809 | 0 | 808 | 809 | 352 | 32 |
LogAroundOne_4096 | 827 | 0 | 826 | 827 | 576 | 32 |
LogMedMag_1 | 1033 | 6 | 1015 | 1113 | 17024 | 32 |
LogMedMag_128 | 606 | 2 | 603 | 610 | 1344 | 32 |
LogMedMag_1024 | 809 | 0 | 808 | 809 | 352 | 32 |
LogMedMag_4096 | 827 | 0 | 827 | 827 | 352 | 32 |
LogNormal_1 | 1033 | 4 | 1020 | 1040 | 1344 | 32 |
LogNormal_128 | 607 | 2 | 604 | 609 | 352 | 32 |
LogNormal_1024 | 809 | 0 | 808 | 810 | 2880 | 32 |
LogNormal_4096 | 827 | 0 | 826 | 827 | 352 | 32 |
NvLogSubnormal_1 | 1403 | 10 | 1403 | 1735 | 33856 | 32 |
NvLogSubnormal_128 | 1341 | 0 | 1341 | 1341 | 352 | 32 |
NvLogSubnormal_1024 | 1552 | 0 | 1552 | 1552 | 352 | 32 |
NvLogSubnormal_4096 | 1574 | 0 | 1574 | 1575 | 352 | 32 |
NvLogAroundOne_1 | 1397 | 5 | 1397 | 1473 | 8480 | 32 |
NvLogAroundOne_128 | 1341 | 0 | 1341 | 1342 | 352 | 32 |
NvLogAroundOne_1024 | 1572 | 0 | 1572 | 1572 | 352 | 32 |
NvLogAroundOne_4096 | 1593 | 0 | 1593 | 1593 | 352 | 32 |
NvLogMedMag_1 | 1403 | 4 | 1403 | 1473 | 8480 | 32 |
NvLogMedMag_128 | 1342 | 0 | 1342 | 1344 | 576 | 32 |
NvLogMedMag_1024 | 1554 | 0 | 1554 | 1554 | 352 | 32 |
NvLogMedMag_4096 | 1575 | 0 | 1575 | 1576 | 352 | 32 |
NvLogNormal_1 | 1403 | 10 | 1403 | 1722 | 33856 | 32 |
NvLogNormal_128 | 1342 | 0 | 1342 | 1342 | 352 | 32 |
NvLogNormal_1024 | 1554 | 0 | 1553 | 1554 | 352 | 32 |
NvLogNormal_4096 | 1575 | 0 | 1575 | 1576 | 352 | 32 |
[8/10] Running hermetic test libc.benchmarks.gpu.src.math.logf_benchmark
Running Suite: LlvmLibcLogfGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
LogfSubnormal_1 | 1048 | 8 | 1036 | 1325 | 47616 | 32 |
LogfSubnormal_128 | 495 | 2 | 491 | 498 | 1984 | 32 |
LogfSubnormal_1024 | 696 | 0 | 694 | 696 | 1344 | 32 |
LogfSubnormal_4096 | 715 | 0 | 715 | 715 | 352 | 32 |
LogfAroundOne_1 | 1047 | 5 | 1035 | 1104 | 5952 | 32 |
LogfAroundOne_128 | 496 | 2 | 492 | 500 | 2880 | 32 |
LogfAroundOne_1024 | 696 | 0 | 695 | 696 | 576 | 32 |
LogfAroundOne_4096 | 715 | 0 | 715 | 715 | 352 | 32 |
LogfMedMag_1 | 1047 | 8 | 1035 | 1649 | 258688 | 32 |
LogfMedMag_128 | 495 | 2 | 491 | 498 | 1984 | 32 |
LogfMedMag_1024 | 696 | 0 | 695 | 696 | 576 | 32 |
LogfMedMag_4096 | 715 | 0 | 715 | 716 | 576 | 32 |
LogfNormal_1 | 1094 | 5 | 1081 | 1104 | 1984 | 32 |
LogfNormal_128 | 540 | 1 | 538 | 543 | 576 | 32 |
LogfNormal_1024 | 741 | 1 | 740 | 742 | 576 | 32 |
LogfNormal_4096 | 761 | 0 | 761 | 761 | 352 | 32 |
NvLogfSubnormal_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvLogfSubnormal_128 | 94 | 0 | 94 | 94 | 576 | 32 |
NvLogfSubnormal_1024 | 302 | 0 | 301 | 302 | 896 | 32 |
NvLogfSubnormal_4096 | 325 | 0 | 325 | 325 | 352 | 32 |
NvLogfAroundOne_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvLogfAroundOne_128 | 94 | 0 | 94 | 94 | 576 | 32 |
NvLogfAroundOne_1024 | 302 | 0 | 302 | 302 | 352 | 32 |
NvLogfAroundOne_4096 | 325 | 0 | 325 | 325 | 352 | 32 |
NvLogfMedMag_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvLogfMedMag_128 | 94 | 0 | 94 | 94 | 576 | 32 |
NvLogfMedMag_1024 | 302 | 0 | 302 | 302 | 352 | 32 |
NvLogfMedMag_4096 | 325 | 0 | 325 | 325 | 352 | 32 |
NvLogfNormal_1 | 61 | 0 | 61 | 61 | 1344 | 32 |
NvLogfNormal_128 | 94 | 0 | 94 | 94 | 576 | 32 |
NvLogfNormal_1024 | 302 | 0 | 302 | 302 | 352 | 32 |
NvLogfNormal_4096 | 325 | 0 | 325 | 325 | 352 | 32 |
[9/10] Running hermetic test libc.benchmarks.gpu.src.math.logf16_benchmark
Running Suite: LlvmLibcLogf16GpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
Logf16Subnormal_1 | 763 | 2 | 759 | 767 | 1344 | 32 |
Logf16Subnormal_128 | 176 | 1 | 176 | 206 | 24032 | 32 |
Logf16Subnormal_1024 | 174 | 1 | 174 | 195 | 17024 | 32 |
Logf16Subnormal_4096 | 292 | 0 | 291 | 292 | 1344 | 32 |
Logf16AroundOne_1 | 762 | 8 | 757 | 848 | 8480 | 32 |
Logf16AroundOne_128 | 176 | 1 | 176 | 180 | 5952 | 32 |
Logf16AroundOne_1024 | 173 | 1 | 172 | 176 | 1984 | 32 |
Logf16AroundOne_4096 | 292 | 0 | 292 | 293 | 896 | 32 |
Logf16MedMag_1 | 764 | 7 | 759 | 849 | 5952 | 32 |
Logf16MedMag_128 | 176 | 0 | 176 | 176 | 576 | 32 |
Logf16MedMag_1024 | 172 | 1 | 172 | 188 | 17024 | 32 |
Logf16MedMag_4096 | 292 | 0 | 292 | 292 | 352 | 32 |
Logf16Normal_1 | 763 | 2 | 759 | 768 | 2880 | 32 |
Logf16Normal_128 | 176 | 0 | 176 | 176 | 576 | 32 |
Logf16Normal_1024 | 172 | 1 | 172 | 196 | 24032 | 32 |
Logf16Normal_4096 | 292 | 0 | 292 | 292 | 352 | 32 |
[10/10] Running hermetic test libc.benchmarks.gpu.src.math.sin_benchmark
Running Suite: LlvmLibcSinGpuBenchmark
Benchmark | Cycles (Mean) | Stddev | Min | Max | Iterations | Threads |
------------------------------------------------------------------------------------------------------
Sin_1 | 3124 | 153 | 2965 | 3658 | 996096 | 32 |
Sin_128 | 2696 | 15 | 2651 | 2739 | 17024 | 32 |
Sin_1024 | 2880 | 5 | 2871 | 2890 | 1344 | 32 |
Sin_4096 | 2894 | 2 | 2890 | 2898 | 352 | 32 |
SinTwoPi_1 | 2217 | 12 | 2202 | 2516 | 24032 | 32 |
SinTwoPi_128 | 2047 | 2 | 2044 | 2051 | 1344 | 32 |
SinTwoPi_1024 | 2253 | 0 | 2252 | 2253 | 352 | 32 |
SinTwoPi_4096 | 2271 | 0 | 2271 | 2271 | 352 | 32 |
SinTwoPow30_1 | 3133 | 17 | 3110 | 3358 | 8480 | 32 |
SinTwoPow30_128 | 2734 | 1 | 2732 | 2736 | 352 | 32 |
SinTwoPow30_1024 | 2940 | 0 | 2940 | 2940 | 352 | 32 |
SinTwoPow30_4096 | 2958 | 0 | 2958 | 2958 | 352 | 32 |
SinVeryLarge_1 | 2855 | 18 | 2817 | 3090 | 5952 | 32 |
SinVeryLarge_128 | 2401 | 3 | 2398 | 2406 | 352 | 32 |
SinVeryLarge_1024 | 2599 | 1 | 2598 | 2600 | 352 | 32 |
SinVeryLarge_4096 | 2614 | 0 | 2614 | 2615 | 352 | 32 |
NvSin_1 | 2520 | 69 | 2260 | 2877 | 5952 | 32 |
NvSin_128 | 1826 | 2 | 1824 | 1830 | 576 | 32 |
NvSin_1024 | 2035 | 1 | 2034 | 2036 | 352 | 32 |
NvSin_4096 | 2052 | 0 | 2052 | 2053 | 352 | 32 |
NvSinTwoPi_1 | 1106 | 1 | 1104 | 1108 | 1344 | 32 |
NvSinTwoPi_128 | 891 | 0 | 891 | 891 | 352 | 32 |
NvSinTwoPi_1024 | 1101 | 0 | 1101 | 1101 | 352 | 32 |
NvSinTwoPi_4096 | 1121 | 0 | 1121 | 1121 | 352 | 32 |
NvSinTwoPow30_1 | 1106 | 1 | 1103 | 1108 | 1344 | 32 |
NvSinTwoPow30_128 | 891 | 0 | 891 | 891 | 352 | 32 |
NvSinTwoPow30_1024 | 1101 | 0 | 1101 | 1101 | 352 | 32 |
NvSinTwoPow30_4096 | 1121 | 0 | 1121 | 1121 | 352 | 32 |
NvSinVeryLarge_1 | 2495 | 23 | 2251 | 2844 | 12032 | 32 |
NvSinVeryLarge_128 | 1791 | 1 | 1790 | 1793 | 576 | 32 |
NvSinVeryLarge_1024 | 1998 | 0 | 1998 | 1999 | 352 | 32 |
NvSinVeryLarge_4096 | 2018 | 0 | 2018 | 2019 | 352 | 32 |
Sinf_1 | 2200 | 170 | 1520 | 2400 | 507776 | 32 |
Sinf_128 | 1872 | 13 | 1830 | 1898 | 2880 | 32 |
Sinf_1024 | 2057 | 5 | 2050 | 2067 | 352 | 32 |
Sinf_4096 | 2092 | 3 | 2088 | 2097 | 352 | 32 |
SinfTwoPi_1 | 1442 | 11 | 1426 | 1761 | 33856 | 32 |
SinfTwoPi_128 | 1126 | 1 | 1125 | 1129 | 352 | 32 |
SinfTwoPi_1024 | 1313 | 0 | 1313 | 1314 | 352 | 32 |
SinfTwoPi_4096 | 1349 | 0 | 1349 | 1349 | 352 | 32 |
SinfTwoPow30_1 | 1087 | 10 | 1079 | 1161 | 1984 | 32 |
SinfTwoPow30_128 | 771 | 1 | 771 | 774 | 1984 | 32 |
SinfTwoPow30_1024 | 960 | 0 | 960 | 961 | 352 | 32 |
SinfTwoPow30_4096 | 996 | 0 | 996 | 996 | 352 | 32 |
SinfVeryLarge_1 | 1925 | 14 | 1869 | 2275 | 24032 | 32 |
SinfVeryLarge_128 | 1598 | 1 | 1598 | 1600 | 352 | 32 |
SinfVeryLarge_1024 | 1787 | 1 | 1786 | 1789 | 576 | 32 |
SinfVeryLarge_4096 | 1823 | 0 | 1823 | 1823 | 352 | 32 |
NvSinf_1 | 1023 | 6 | 1018 | 1039 | 5952 | 32 |
NvSinf_128 | 742 | 0 | 742 | 744 | 576 | 32 |
NvSinf_1024 | 931 | 0 | 931 | 932 | 352 | 32 |
NvSinf_4096 | 967 | 0 | 967 | 967 | 352 | 32 |
NvSinfTwoPi_1 | 162 | 3 | 162 | 499 | 362464 | 32 |
NvSinfTwoPi_128 | 107 | 0 | 107 | 109 | 2880 | 32 |
NvSinfTwoPi_1024 | 296 | 0 | 296 | 297 | 896 | 32 |
NvSinfTwoPi_4096 | 333 | 0 | 333 | 333 | 352 | 32 |
NvSinfTwoPow30_1 | 1025 | 11 | 1018 | 1280 | 33856 | 32 |
NvSinfTwoPow30_128 | 742 | 0 | 741 | 742 | 352 | 32 |
NvSinfTwoPow30_1024 | 931 | 0 | 931 | 931 | 352 | 32 |
NvSinfTwoPow30_4096 | 966 | 0 | 966 | 966 | 352 | 32 |
NvSinfVeryLarge_1 | 1002 | 1 | 1000 | 1004 | 1344 | 32 |
NvSinfVeryLarge_128 | 723 | 0 | 723 | 723 | 352 | 32 |
NvSinfVeryLarge_1024 | 912 | 0 | 912 | 913 | 576 | 32 |
NvSinfVeryLarge_4096 | 948 | 0 | 948 | 948 | 352 | 32 |
```
https://github.com/llvm/llvm-project/pull/155727
More information about the libc-commits
mailing list