llvm-project/libc/config/linux · openEuler/llvm-project

TTue Ly[libc][math] Implement erff function correctly rounded to all rounding modes.

f320fefc创建于 2023年6月29日历史提交

文件	最后提交记录	最后更新时间
aarch64	[libc][math] Implement erff function correctly rounded to all rounding modes. Implement correctly rounded `erff` functions. For `x >= 4`, `erff(x) = 1` for `FE_TONEAREST` or `FE_UPWARD`, `0x1.ffffep-1` for `FE_DOWNWARD` or `FE_TOWARDZERO`. For `0 <= x < 4`, we divide into 32 sub-intervals of length `1/8`, and use a degree-15 odd polynomial to approximate `erff(x)` in each sub-interval: `erff(x) ~ x * (c0 + c1 * x^2 + c2 * x^4 + ... + c7 * x^14).` For `x < 0`, we can use the same formula as above, since the odd part is factored out. Performance tested with `perf.sh` tool from the CORE-MATH project on AMD Ryzen 9 5900X: Reciprocal throughput (clock cycles / op) $ ./perf.sh erff --path2 GNU libc version: 2.35 GNU libc release: stable -- CORE-MATH reciprocal throughput -- with -march=native (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 11.790 + 0.182 clc/call; Median-Min = 0.154 clc/call; Max = 12.255 clc/call; -- CORE-MATH reciprocal throughput -- with -march=x86-64-v2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 14.205 + 0.151 clc/call; Median-Min = 0.159 clc/call; Max = 15.893 clc/call; -- System LIBC reciprocal throughput -- [####################] 100 % Ntrial = 20 ; Min = 45.519 + 0.445 clc/call; Median-Min = 0.552 clc/call; Max = 46.345 clc/call; -- LIBC reciprocal throughput -- with -mavx2 -mfma (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 9.595 + 0.214 clc/call; Median-Min = 0.220 clc/call; Max = 9.887 clc/call; -- LIBC reciprocal throughput -- with -msse4.2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 10.223 + 0.190 clc/call; Median-Min = 0.222 clc/call; Max = 10.474 clc/call; and latency (clock cycles / op): $ ./perf.sh erff --path2 GNU libc version: 2.35 GNU libc release: stable -- CORE-MATH latency -- with -march=native (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 38.566 + 0.391 clc/call; Median-Min = 0.503 clc/call; Max = 39.170 clc/call; -- CORE-MATH latency -- with -march=x86-64-v2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 43.223 + 0.667 clc/call; Median-Min = 0.680 clc/call; Max = 43.913 clc/call; -- System LIBC latency -- [####################] 100 % Ntrial = 20 ; Min = 111.613 + 1.267 clc/call; Median-Min = 1.696 clc/call; Max = 113.444 clc/call; -- LIBC latency -- with -mavx2 -mfma (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 40.138 + 0.410 clc/call; Median-Min = 0.536 clc/call; Max = 40.729 clc/call; -- LIBC latency -- with -msse4.2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 44.858 + 0.872 clc/call; Median-Min = 0.814 clc/call; Max = 46.019 clc/call; Reviewed By: michaelrj Differential Revision: https://reviews.llvm.org/D153683	3 年前
arm	[libc] Add qsort_r This patch adds the reentrent qsort entrypoint, qsort_r. This is done by extending the qsort functionality and moving it to a shared utility header. For this reason the qsort_r tests focus mostly on the places where it differs from qsort, since they share the same sorting code. Reviewed By: sivachandra, lntue Differential Revision: https://reviews.llvm.org/D152467	3 年前
riscv64	[libc][math] Implement erff function correctly rounded to all rounding modes. Implement correctly rounded `erff` functions. For `x >= 4`, `erff(x) = 1` for `FE_TONEAREST` or `FE_UPWARD`, `0x1.ffffep-1` for `FE_DOWNWARD` or `FE_TOWARDZERO`. For `0 <= x < 4`, we divide into 32 sub-intervals of length `1/8`, and use a degree-15 odd polynomial to approximate `erff(x)` in each sub-interval: `erff(x) ~ x * (c0 + c1 * x^2 + c2 * x^4 + ... + c7 * x^14).` For `x < 0`, we can use the same formula as above, since the odd part is factored out. Performance tested with `perf.sh` tool from the CORE-MATH project on AMD Ryzen 9 5900X: Reciprocal throughput (clock cycles / op) $ ./perf.sh erff --path2 GNU libc version: 2.35 GNU libc release: stable -- CORE-MATH reciprocal throughput -- with -march=native (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 11.790 + 0.182 clc/call; Median-Min = 0.154 clc/call; Max = 12.255 clc/call; -- CORE-MATH reciprocal throughput -- with -march=x86-64-v2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 14.205 + 0.151 clc/call; Median-Min = 0.159 clc/call; Max = 15.893 clc/call; -- System LIBC reciprocal throughput -- [####################] 100 % Ntrial = 20 ; Min = 45.519 + 0.445 clc/call; Median-Min = 0.552 clc/call; Max = 46.345 clc/call; -- LIBC reciprocal throughput -- with -mavx2 -mfma (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 9.595 + 0.214 clc/call; Median-Min = 0.220 clc/call; Max = 9.887 clc/call; -- LIBC reciprocal throughput -- with -msse4.2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 10.223 + 0.190 clc/call; Median-Min = 0.222 clc/call; Max = 10.474 clc/call; and latency (clock cycles / op): $ ./perf.sh erff --path2 GNU libc version: 2.35 GNU libc release: stable -- CORE-MATH latency -- with -march=native (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 38.566 + 0.391 clc/call; Median-Min = 0.503 clc/call; Max = 39.170 clc/call; -- CORE-MATH latency -- with -march=x86-64-v2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 43.223 + 0.667 clc/call; Median-Min = 0.680 clc/call; Max = 43.913 clc/call; -- System LIBC latency -- [####################] 100 % Ntrial = 20 ; Min = 111.613 + 1.267 clc/call; Median-Min = 1.696 clc/call; Max = 113.444 clc/call; -- LIBC latency -- with -mavx2 -mfma (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 40.138 + 0.410 clc/call; Median-Min = 0.536 clc/call; Max = 40.729 clc/call; -- LIBC latency -- with -msse4.2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 44.858 + 0.872 clc/call; Median-Min = 0.814 clc/call; Max = 46.019 clc/call; Reviewed By: michaelrj Differential Revision: https://reviews.llvm.org/D153683	3 年前
x86_64	[libc][math] Implement erff function correctly rounded to all rounding modes. Implement correctly rounded `erff` functions. For `x >= 4`, `erff(x) = 1` for `FE_TONEAREST` or `FE_UPWARD`, `0x1.ffffep-1` for `FE_DOWNWARD` or `FE_TOWARDZERO`. For `0 <= x < 4`, we divide into 32 sub-intervals of length `1/8`, and use a degree-15 odd polynomial to approximate `erff(x)` in each sub-interval: `erff(x) ~ x * (c0 + c1 * x^2 + c2 * x^4 + ... + c7 * x^14).` For `x < 0`, we can use the same formula as above, since the odd part is factored out. Performance tested with `perf.sh` tool from the CORE-MATH project on AMD Ryzen 9 5900X: Reciprocal throughput (clock cycles / op) $ ./perf.sh erff --path2 GNU libc version: 2.35 GNU libc release: stable -- CORE-MATH reciprocal throughput -- with -march=native (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 11.790 + 0.182 clc/call; Median-Min = 0.154 clc/call; Max = 12.255 clc/call; -- CORE-MATH reciprocal throughput -- with -march=x86-64-v2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 14.205 + 0.151 clc/call; Median-Min = 0.159 clc/call; Max = 15.893 clc/call; -- System LIBC reciprocal throughput -- [####################] 100 % Ntrial = 20 ; Min = 45.519 + 0.445 clc/call; Median-Min = 0.552 clc/call; Max = 46.345 clc/call; -- LIBC reciprocal throughput -- with -mavx2 -mfma (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 9.595 + 0.214 clc/call; Median-Min = 0.220 clc/call; Max = 9.887 clc/call; -- LIBC reciprocal throughput -- with -msse4.2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 10.223 + 0.190 clc/call; Median-Min = 0.222 clc/call; Max = 10.474 clc/call; and latency (clock cycles / op): $ ./perf.sh erff --path2 GNU libc version: 2.35 GNU libc release: stable -- CORE-MATH latency -- with -march=native (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 38.566 + 0.391 clc/call; Median-Min = 0.503 clc/call; Max = 39.170 clc/call; -- CORE-MATH latency -- with -march=x86-64-v2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 43.223 + 0.667 clc/call; Median-Min = 0.680 clc/call; Max = 43.913 clc/call; -- System LIBC latency -- [####################] 100 % Ntrial = 20 ; Min = 111.613 + 1.267 clc/call; Median-Min = 1.696 clc/call; Max = 113.444 clc/call; -- LIBC latency -- with -mavx2 -mfma (with FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 40.138 + 0.410 clc/call; Median-Min = 0.536 clc/call; Max = 40.729 clc/call; -- LIBC latency -- with -msse4.2 (without FMA instructions) [####################] 100 % Ntrial = 20 ; Min = 44.858 + 0.872 clc/call; Median-Min = 0.814 clc/call; Max = 46.019 clc/call; Reviewed By: michaelrj Differential Revision: https://reviews.llvm.org/D153683	3 年前
CMakeLists.txt	[libc][Obvious] Convert an add_header target to add_header_library target.	3 年前
api.td	[libc] Add qsort_r This patch adds the reentrent qsort entrypoint, qsort_r. This is done by extending the qsort functionality and moving it to a shared utility header. For this reason the qsort_r tests focus mostly on the places where it differs from qsort, since they share the same sorting code. Reviewed By: sivachandra, lntue Differential Revision: https://reviews.llvm.org/D152467	3 年前
app.h	[libc] Extend the linux thread implementation for riscv64. Also, added riscv64 startup code for static linking which is used by the integration tests. Functions from the C standard threads library have been enabled. Reviewed By: mikhail.ramalho Differential Revision: https://reviews.llvm.org/D145670	3 年前
platform_defs.h.inc	[libc] Fix typo in platform_defs.h.inc Differential Revision: https://reviews.llvm.org/D87687	5 年前
signal.h.in	[libc][NFC] Make all top of file comments consistent. Summary: Made all header files consistent based of this documentation: https://llvm.org/docs/CodingStandards.html#file-headers. And did the same for all source files top of file comments. Reviewers: sivachandra, abrachet Reviewed By: sivachandra, abrachet Subscribers: MaskRay, tschuett, libc-commits Tags: #libc-project Differential Revision: https://reviews.llvm.org/D77533	6 年前
syscall_numbers.h.inc	Add implementations of POSIX mmap and munmap functions. Summary: A set of of linux x86_64 internal syscall helpers have also been added. This change does not try to be perfect with respect to OS and machine abstractions. A TODO note has been added at places where such abstractions would help and make the arrangement scalable and cleaner. Addressing the TODOs and building such abstractions is not in the scope of this change. It is hoped that follow up changes cleaning up the problem areas and addressing the TODOs will better illustrate the need for the changes. This change also does not try to imitate mmap and munmap implementations of other libcs. The idea here is to put in the bare minimum required to obtain a working mmap and munmap, and then add the rest of the functionality on an as needed basis. Reviewers: abrachet, phosek, stanshebs, theraven Subscribers: mgorny, MaskRay, jfb, libc-commits Tags: #libc-project Differential Revision: https://reviews.llvm.org/D71634	6 年前