Created
February 16, 2018 22:30
-
-
Save abadams/58aef3941e678b90bc9937d9005d0051 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Halide: | |
1.42 │ e0: vmovup -0x60(%rdi),%ymm0 | |
4.50 │ vmovup -0x40(%rdi),%ymm6 | |
4.97 │ vmovup -0x20(%rdi),%ymm7 | |
2.54 │ vmovup (%rdi),%ymm8 | |
30.71 │ vfmadd (%rsi),%ymm5,%ymm8 | |
7.82 │ vfmadd -0x20(%rsi),%ymm5,%ymm7 | |
22.69 │ vfmadd -0x40(%rsi),%ymm5,%ymm6 | |
5.42 │ vfmadd -0x60(%rsi),%ymm5,%ymm0 | |
2.74 │ vmovup %ymm0,-0x60(%rsi) | |
2.40 │ vmovup %ymm6,-0x40(%rsi) | |
2.15 │ vmovup %ymm7,-0x20(%rsi) | |
1.03 │ vmovup %ymm8,(%rsi) | |
2.96 │ sub $0xffffffffffffff80,%rsi | |
5.06 │ sub $0xffffffffffffff80,%rdi | |
0.08 │ add $0xffffffffffffffff,%rbp | |
2.07 │ ↑ jne e0 | |
Openblas: | |
1.25 │10: vmovup (%rdx,%rax,4),%ymm12 | |
21.01 │ vmovup 0x20(%rdx,%rax,4),%ymm13 | |
3.29 │ vmovup 0x40(%rdx,%rax,4),%ymm14 | |
20.35 │ vmovup 0x60(%rdx,%rax,4),%ymm15 | |
8.39 │ vfmadd (%rsi,%rax,4),%ymm0,%ymm12 | |
8.46 │ vfmadd 0x20(%rsi,%rax,4),%ymm0,%ymm13 | |
9.95 │ vfmadd 0x40(%rsi,%rax,4),%ymm0,%ymm14 | |
11.35 │ vfmadd 0x60(%rsi,%rax,4),%ymm0,%ymm15 | |
0.09 │ vmovup %ymm12,(%rdx,%rax,4) | |
2.95 │ vmovup %ymm13,0x20(%rdx,%rax,4) | |
0.13 │ vmovup %ymm14,0x40(%rdx,%rax,4) | |
7.65 │ vmovup %ymm15,0x60(%rdx,%rax,4) | |
0.01 │ add $0x20,%rax | |
0.06 │ sub $0x20,%rdi | |
4.65 │ ↑ jne 10 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment