add a note
authorChris Lattner <sabre@nondot.org>
Sun, 2 Apr 2006 03:59:11 +0000 (03:59 +0000)
committerChris Lattner <sabre@nondot.org>
Sun, 2 Apr 2006 03:59:11 +0000 (03:59 +0000)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27348 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/PowerPC/README_ALTIVEC.txt

index 824dc6cafcf18f0db859f74a27b56a25890259eb..881ba020f42ef1b15be4e2db5d7ae3a2742ddc85 100644 (file)
@@ -137,3 +137,14 @@ Instcombine llvm.ppc.altivec.vperm with an immediate into a shuffle operation.
 
 Handle VECTOR_SHUFFLE nodes with the appropriate shuffle mask with vsldoi,
 vpkuhum and vpkuwum.
+
+//===----------------------------------------------------------------------===//
+
+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;
+}
+
+//===----------------------------------------------------------------------===//