Comparing
llvm-nightly-test
(32abcf0
) withmain
(db60537
)-32%
- Regression
- 10
- Untouched
- 330
Benchmarks
340 total
test_elemwise[f=<built-in function mul>-backend='Finch'-side=100]
benchmarks/test_elemwise.py-32%
694 µs1,021.2 µs
test_elemwise[f=<built-in function mul>-backend='Finch'-side=500]
benchmarks/test_elemwise.py-32%
713.3 µs1,045.9 µs
test_elemwise[f=<built-in function add>-backend='Finch'-side=100]
benchmarks/test_elemwise.py-31%
713.7 µs1,037.5 µs
test_elemwise[f=<built-in function mul>-backend='Finch'-side=1000]
benchmarks/test_elemwise.py-31%
736.4 µs1,068.9 µs
test_elemwise[f=<built-in function add>-backend='Finch'-side=500]
benchmarks/test_elemwise.py-25%
882.4 µs1,175.5 µs
test_elemwise[f=<built-in function gt>-backend='Finch'-side=100]
benchmarks/test_elemwise.py-25%
708.9 µs940.2 µs
test_elemwise[f=<built-in function gt>-backend='Finch'-side=500]
benchmarks/test_elemwise.py-21%
879.6 µs1,109.9 µs
test_index_slice[side=100-rank=2-format='gcxs']
benchmarks/test_benchmark_coo.py-20%
2.2 ms2.7 ms
test_elemwise[f=<built-in function add>-backend='Finch'-side=1000]
benchmarks/test_elemwise.py-17%
1.5 ms1.8 ms
test_elemwise[f=<built-in function gt>-backend='Finch'-side=1000]
benchmarks/test_elemwise.py-14%
1.4 ms1.7 ms
test_elemwise[f=<built-in function add>-backend='Numba'-side=100]
benchmarks/test_elemwise.py+4%
4 ms3.8 ms
test_elemwise[f=<built-in function add>-backend='Numba'-side=500]
benchmarks/test_elemwise.py+4%
4.4 ms4.2 ms
test_index_fancy[side=100-rank=3-format='coo']
benchmarks/test_benchmark_coo.py+2%
3.6 ms3.5 ms
test_index_fancy[side=1000-rank=2-format='gcxs']
benchmarks/test_benchmark_coo.py+2%
6.6 ms6.5 ms
test_index_fancy[side=100-rank=3-format='gcxs']
benchmarks/test_benchmark_coo.py+2%
7.2 ms7.1 ms
test_tensordot[left_index=1-right_index=1-left_format='coo'-right_format='dense'-m=10-n=20-p=50-q=50-COO]
benchmarks/test_tensordot.py+1%
4 ms4 ms
test_index_fancy[side=1000-rank=2-format='coo']
benchmarks/test_benchmark_coo.py+1%
4.6 ms4.5 ms
test_matmul[m=200-n=1000-p=1000-gcxs]
benchmarks/test_benchmark_coo.py+1%
8 ms7.9 ms
test_matmul[m=500-n=1000-p=500-coo]
benchmarks/test_benchmark_coo.py+1%
12.3 ms12.2 ms
test_tensordot[left_index=1-right_index=1-left_format='coo'-right_format='dense'-m=50-n=10-p=50-q=10-COO]
benchmarks/test_tensordot.py+1%
2.7 ms2.7 ms
test_elemwise[side=100-rank=3-format='coo'-add]
benchmarks/test_benchmark_coo.py+1%
22.1 ms21.9 ms
test_index_scalar[side=500-rank=2-format='gcxs']
benchmarks/test_benchmark_coo.py+1%
1.5 ms1.5 ms
test_matmul[m=500-n=1000-p=500-gcxs]
benchmarks/test_benchmark_coo.py+1%
16.2 ms16.1 ms
test_index_scalar[side=1000-rank=2-format='gcxs']
benchmarks/test_benchmark_coo.py+1%
1.5 ms1.5 ms
test_index_scalar[side=100-rank=2-format='gcxs']
benchmarks/test_benchmark_coo.py+1%
1.5 ms1.5 ms
Commits
Click on a commit to change the comparison rangeBase
main
db60537
-32.04%
ENH: Update MLIR backend to LLVM 20.dev
32abcf0
1 year ago
by mtsokol