llvm-project/llvm/test/CodeGen/X86/2008-08-17-UComiCodeGenBug.ll

; RUN: llc < %s -mtriple=x86_64-apple-darwin | grep movzbl

define i32 @foo(<4 x float> %a, <4 x float> %b) nounwind {
entry:
	tail call i32 @llvm.x86.sse.ucomige.ss( <4 x float> %a, <4 x float> %b ) nounwind readnone
	ret i32 %0
}

declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone
As Dan pointed out, movzbl, movsbl, and friends are nicer than their alias (movzx/movsx) because they give more information. Revert that part of the patch. llvm-svn: 129498 2011-04-14 09:46:37 +08:00			`; RUN: llc < %s -mtriple=x86_64-apple-darwin \| grep movzbl`
Fix a (u)comiss intrinsic lowering bug. It was using anyext which can return junk in higher bits. Patch by Nate Begeman. llvm-svn: 54903 2008-08-18 03:22:34 +08:00
			`define i32 @foo(<4 x float> %a, <4 x float> %b) nounwind {`
			`entry:`
As Dan pointed out, movzbl, movsbl, and friends are nicer than their alias (movzx/movsx) because they give more information. Revert that part of the patch. llvm-svn: 129498 2011-04-14 09:46:37 +08:00			`tail call i32 @llvm.x86.sse.ucomige.ss( <4 x float> %a, <4 x float> %b ) nounwind readnone`
			`ret i32 %0`
Fix a (u)comiss intrinsic lowering bug. It was using anyext which can return junk in higher bits. Patch by Nate Begeman. llvm-svn: 54903 2008-08-18 03:22:34 +08:00			`}`

			`declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone`