R600/SI: Expand urem of v2i32/v4i32 for SI

Also add lit test for both cases on SI, and v2i32 for evergreen.

Note: I followed the guidance of the v4i32 EG check... UREM produces really
complex code, so let's just check that the instruction was lowered
successfully.

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184844 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Aaron Watry 2013-06-25 13:55:46 +00:00
parent e80978f9dd
commit 41f3db569c
2 changed files with 26 additions and 4 deletions

View File

@ -90,6 +90,9 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
setOperationAction(ISD::UDIV, MVT::v2i32, Expand);
setOperationAction(ISD::UDIV, MVT::v4i32, Expand);
setOperationAction(ISD::UREM, MVT::v2i32, Expand);
setOperationAction(ISD::UREM, MVT::v4i32, Expand);
setOperationAction(ISD::SELECT_CC, MVT::f32, Custom);
setOperationAction(ISD::SELECT_CC, MVT::i32, Custom);

View File

@ -1,11 +1,30 @@
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK %s
;RUN: llc < %s -march=r600 -mcpu=verde | FileCheck --check-prefix=SI-CHECK %s
;The code generated by urem is long and complex and may frequently change.
;The goal of this test is to make sure the ISel doesn't fail when it gets
;a v4i32 urem
;CHECK: CF_END
;a v2i32/v4i32 urem
define void @test(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
;EG-CHECK: @test2
;EG-CHECK: CF_END
;SI-CHECK: @test2
;SI-CHECK: S_ENDPGM
define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
%b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
%a = load <2 x i32> addrspace(1) * %in
%b = load <2 x i32> addrspace(1) * %b_ptr
%result = urem <2 x i32> %a, %b
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
ret void
}
;EG-CHECK: @test4
;EG-CHECK: CF_END
;SI-CHECK: @test4
;SI-CHECK: S_ENDPGM
define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
%b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
%a = load <4 x i32> addrspace(1) * %in
%b = load <4 x i32> addrspace(1) * %b_ptr