From 53ff5ae8a172f4fc7f821b039e794fe36c4d68b9 Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Mon, 5 Mar 2018 23:00:39 +0000 Subject: [PATCH] [X86] cvttpd2dq lowering has been supported for some time Tests in vec_fp_to_int.ll llvm-svn: 326751 --- llvm/lib/Target/X86/README-SSE.txt | 9 --------- 1 file changed, 9 deletions(-) diff --git a/llvm/lib/Target/X86/README-SSE.txt b/llvm/lib/Target/X86/README-SSE.txt index 73cf276..190ca86 100644 --- a/llvm/lib/Target/X86/README-SSE.txt +++ b/llvm/lib/Target/X86/README-SSE.txt @@ -839,12 +839,3 @@ similarly, v[0]-v[1] should match to hsubpd, and {v[0]-v[1], w[0]-w[1]} should turn into hsubpd also. //===---------------------------------------------------------------------===// - -define <2 x i32> @foo(<2 x double> %in) { - %x = fptosi <2 x double> %in to <2 x i32> - ret <2 x i32> %x -} - -Should compile into cvttpd2dq instead of being scalarized into 2 cvttsd2si. - -//===---------------------------------------------------------------------===// -- 2.7.4