R600/SI: Expand udiv v[24]i32 for SI and v2i32 for EG

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

Note: I followed the guidance of the v4i32 EG check... UDIV 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@184843 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp
index 812df8359d38d0098907d13cc77f7add99ca9428..cf349a83f6ed98bf6d91c15b2948027adad0ac6a 100644 (file)
--- a/lib/Target/R600/R600ISelLowering.cpp
+++ b/lib/Target/R600/R600ISelLowering.cpp
@@ -56,6 +56,7 @@ R600TargetLowering::R600TargetLowering(TargetMachine &TM) :
   setOperationAction(ISD::SUB, MVT::v4i32, Expand);
   setOperationAction(ISD::SUB, MVT::v2i32, Expand);
   setOperationAction(ISD::UINT_TO_FP, MVT::v4i32, Expand);
+  setOperationAction(ISD::UDIV, MVT::v2i32, Expand);
   setOperationAction(ISD::UDIV, MVT::v4i32, Expand);
   setOperationAction(ISD::UREM, MVT::v4i32, Expand);
   setOperationAction(ISD::SETCC, MVT::v4i32, Expand);

diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp
index 5f44d3ad9c6112c2eaceae5adc62f87c47e99a81..1fb28fac0f160990f6487c924117aa01f95cec10 100644 (file)
--- a/lib/Target/R600/SIISelLowering.cpp
+++ b/lib/Target/R600/SIISelLowering.cpp
@@ -87,6 +87,9 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
   setOperationAction(ISD::SUB, MVT::v2i32, Expand);
   setOperationAction(ISD::SUB, MVT::v4i32, Expand);
 
+  setOperationAction(ISD::UDIV, MVT::v2i32, Expand);
+  setOperationAction(ISD::UDIV, MVT::v4i32, Expand);
+
   setOperationAction(ISD::SELECT_CC, MVT::f32, Custom);
   setOperationAction(ISD::SELECT_CC, MVT::i32, Custom);
 

diff --git a/test/CodeGen/R600/udiv.ll b/test/CodeGen/R600/udiv.ll
index b81e3667ce8976d265ef51f18fdf719e997087b8..08fe2efd77153ed7cff7e69bf010c4d87886c01e 100644 (file)
--- a/test/CodeGen/R600/udiv.ll
+++ b/test/CodeGen/R600/udiv.ll
@@ -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 udiv 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 udiv
-;CHECK: CF_END
 
-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 = udiv <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