llvm/test/CodeGen/AMDGPU/extload-align.ll
Nirav Dave 489cfe73c2 [DAG] Fix incorrect alignment of ext load.
Correctly use alignment size from loaded size not output value size.

Reviewers: jyknight, tstellarAMD, arsenm

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D23356

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282177 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-22 17:28:43 +00:00

23 lines
975 B
LLVM

; RUN: llc -debug-only=misched -march=amdgcn -verify-machineinstrs %s -o - 2>&1| FileCheck -check-prefix=SI-NOHSA -check-prefix=FUNC -check-prefix=DEBUG %s
; REQUIRES: asserts
; Verify that the extload generated from %eval has the default
; alignment size (2) corresponding to the underlying memory size (i16)
; size and not 4 corresponding to the sign-extended size (i32).
; DEBUG: {{^}}# Machine code for function extload_align:
; DEBUG: mem:LD2[<unknown>]{{[^(]}}
; DEBUG: {{^}}# End machine code for function extload_align.
define void @extload_align(i32* %out, i32 %index) #0 {
%v0 = alloca [4 x i16]
%a1 = getelementptr inbounds [4 x i16], [4 x i16]* %v0, i32 0, i32 0
%a2 = getelementptr inbounds [4 x i16], [4 x i16]* %v0, i32 0, i32 1
store i16 0, i16* %a1
store i16 1, i16* %a2
%a = getelementptr inbounds [4 x i16], [4 x i16]* %v0, i32 0, i32 %index
%val = load i16, i16* %a
%eval = sext i16 %val to i32
store i32 %eval, i32* %out
ret void
}