[PATCH] X86 cost model: Adjust cost for custom lowered vector multiplies
Arnold Schwaighofer
aschwaighofer at apple.com
Fri Mar 1 20:04:48 PST 2013
Got an offline LGTM from Nadav.
Committed as 176403.
On Mar 1, 2013, at 5:54 PM, Arnold Schwaighofer <aschwaighofer at apple.com> wrote:
> Adjust cost for custom lowered vector multiplies
>
> This matters for example in following matrix multiply:
>
> int **mmult(int rows, int cols, int **m1, int **m2, int **m3) {
> int i, j, k, val;
> for (i=0; i<rows; i++) {
> for (j=0; j<cols; j++) {
> val = 0;
> for (k=0; k<cols; k++) {
> val += m1[i][k] * m2[k][j];
> }
> m3[i][j] = val;
> }
> }
> return(m3);
> }
>
> Taken from the test-suite benchmark Shootout.
>
> We estimate the cost of the multiply to be 2 while we generate 9 instructions
> for it and end up being quite a bit slower than the scalar version (48% on my
> machine).
>
> Also, properly differentiate between avx1 and avx2. On avx-1 we still split the
> vector into 2 128bits and handle the subvector muls like above with 9
> instructions.
> Only on avx-2 will we have a cost of 9 for v4i64.
>
> I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an
> add instead of a mul because with a mul we now no longer vectorize. I did
> verify that the mul would be indeed more expensive when vectorized with 3
> kernels:
>
> for (i ...)
> r += a[i] * 3;
> for (i ...)
> m1[i] = m1[i] * 3; // This matches the test case in avx1.ll
> and a matrix multiply.
>
> In each case the vectorized version was considerably slower.
>
> radar://13304919
>
> <0001-X86-cost-model-Adjust-cost-for-custom-lowered-vector.patch>
>
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
More information about the llvm-commits
mailing list