vtjnash:jn/zdot_thunderx2t99-ICE - Branch - OpenMathLib/OpenBLAS

arm64: fix clang ICE on Windows for zdot_thunderx2t99.c

#5566Closed

Comparing

vtjnash:jn/zdot_thunderx2t99-ICE

(

d38be78

) with

develop

(

68ff451

)

Untouched: 62

Benchmarks

Passed

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

+1%

24.1 µs23.9 µs

test_dgemv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

+1%

150 µs149.1 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

40.6 µs40.4 µs

test_nrm2[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

30.4 µs30.3 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

103.9 µs103.4 µs

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

141.1 µs140.5 µs

test_dot[100]

benchmark/pybench/benchmarks/bench_blas.py

22.5 µs22.4 µs

test_dgbmv[1-100-d]

benchmark/pybench/benchmarks/bench_blas.py

38 µs37.9 µs

test_nrm2[1000-dz]

benchmark/pybench/benchmarks/bench_blas.py

35.4 µs35.3 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

32.4 µs32.3 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

25.1 µs25.1 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

25.9 µs25.8 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

28.5 µs28.4 µs

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

27.4 µs27.4 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

32.7 µs32.6 µs

test_gesdd[mn0-d]

benchmark/pybench/benchmarks/bench_blas.py

120.2 µs120 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

24.2 µs24.1 µs

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

75 µs74.9 µs

test_syrk[100-s]

benchmark/pybench/benchmarks/bench_blas.py

213.5 µs213.3 µs

test_gesv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

353.6 ms353.4 ms

test_syev[50-d]

benchmark/pybench/benchmarks/bench_blas.py

1.4 ms1.4 ms

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

256.8 µs256.8 µs

test_gesv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

394.1 µs394 µs

test_gesv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

938.2 µs938.1 µs

test_syrk[100-d]

benchmark/pybench/benchmarks/bench_blas.py

339.6 µs339.5 µs

test_syrk[100-c]

benchmark/pybench/benchmarks/bench_blas.py

472.4 µs472.3 µs

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

273.1 µs273.1 µs

test_syev[200-s]

benchmark/pybench/benchmarks/bench_blas.py

49.1 ms49.1 ms

test_dgbmv[1-1000-c]

benchmark/pybench/benchmarks/bench_blas.py

99.5 µs99.4 µs

test_nrm2[100-dz]

benchmark/pybench/benchmarks/bench_blas.py

28.7 µs28.7 µs

test_dgemv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

13.9 ms13.9 ms

test_gesdd[mn1-d]

benchmark/pybench/benchmarks/bench_blas.py

93.9 ms93.8 ms

test_syev[200-d]

benchmark/pybench/benchmarks/bench_blas.py

58.6 ms58.6 ms

test_syrk[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

227.5 ms227.5 ms

test_gesdd[mn1-s]

benchmark/pybench/benchmarks/bench_blas.py

65.2 ms65.2 ms

test_syrk[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

65.4 ms65.4 ms

test_gesv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

93.3 ms93.3 ms

test_gemm[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

117.4 ms117.4 ms

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

471 µs471 µs

test_gemm[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

426 ms426 ms

test_gemm[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

875.6 ms875.6 ms

test_gesv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

188.6 ms188.6 ms

test_syrk[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

476.4 ms476.4 ms

test_dgemv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

26.3 ms26.3 ms

test_syrk[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

130.4 ms130.4 ms

test_dgemv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

14.8 ms14.8 ms

test_gemm[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

239.4 ms239.4 ms

test_gemm[100-z]

benchmark/pybench/benchmarks/bench_blas.py

1.2 ms1.2 ms

test_gesv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

52.6 ms52.6 ms

test_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

695.7 µs695.7 µs

test_dgemv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

7 ms7 ms

test_gemm[100-c]

benchmark/pybench/benchmarks/bench_blas.py

659.5 µs659.5 µs

test_syev[50-s]

benchmark/pybench/benchmarks/bench_blas.py

1.3 ms1.3 ms

test_dgbmv[1-1000-z]

benchmark/pybench/benchmarks/bench_blas.py

118.9 µs118.9 µs

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

231.2 µs231.2 µs

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

40.3 µs40.3 µs

test_dgbmv[1-1000-d]

benchmark/pybench/benchmarks/bench_blas.py

83.5 µs83.6 µs

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

37.2 µs37.3 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

109.1 µs109.3 µs

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

852.9 µs855.3 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

42.1 µs42.3 µs

test_nrm2[100-d]

benchmark/pybench/benchmarks/bench_blas.py

-2%

37.3 µs37.9 µs

Commits

Click on a commit to change the comparison range

Base

develop

68ff451

+0.05%

arm64: fix clang ICE on Windows for zdot_thunderx2t99.c Guard .align directive to avoid internal compiler error on AArch64 Windows with clang. See: https://github.com/llvm/llvm-project/issues/149547 See: #5076 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

d38be78

4 days ago

by vtjnash

Home Terms Privacy Docs