From 19a815238e55458e95f99b4dad31ed053c9f635c Mon Sep 17 00:00:00 2001 From: Chris Lattner Date: Tue, 18 Apr 2006 03:57:35 +0000 Subject: Implement v16i8 multiply with this code: vmuloub v5, v3, v2 vmuleub v2, v3, v2 vperm v2, v2, v5, v4 This implements CodeGen/PowerPC/vec_mul.ll. With this, v16i8 multiplies are 6.79x faster than before. Overall, UnitTests/Vector/multiplies.c is now 2.45x faster with LLVM than with GCC. Remove the 'integer multiplies' todo from the README file. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27792 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Target/PowerPC/README_ALTIVEC.txt | 9 --------- 1 file changed, 9 deletions(-) (limited to 'lib/Target/PowerPC/README_ALTIVEC.txt') diff --git a/lib/Target/PowerPC/README_ALTIVEC.txt b/lib/Target/PowerPC/README_ALTIVEC.txt index 2d91986..9de4415 100644 --- a/lib/Target/PowerPC/README_ALTIVEC.txt +++ b/lib/Target/PowerPC/README_ALTIVEC.txt @@ -75,15 +75,6 @@ be constants. The verifier should enforce this constraint. //===----------------------------------------------------------------------===// -Implement multiply for vector integer types, to avoid the horrible scalarized -code produced by legalize. - -void test(vector int *X, vector int *Y) { - *X = *X * *Y; -} - -//===----------------------------------------------------------------------===// - extract_vector_elt of an arbitrary constant vector can be done with the following instructions: -- cgit v1.1