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

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

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184842 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp
index 4219825ecd3d9021fdc3aa4363eed8ffb4563e56..5f44d3ad9c6112c2eaceae5adc62f87c47e99a81 100644 (file)
--- a/lib/Target/R600/SIISelLowering.cpp
+++ b/lib/Target/R600/SIISelLowering.cpp
@@ -81,6 +81,8 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
   setOperationAction(ISD::SHL, MVT::v4i32, Expand);
   setOperationAction(ISD::SRL, MVT::v4i32, Expand);
   setOperationAction(ISD::SRL, MVT::v2i32, Expand);
+  setOperationAction(ISD::SRA, MVT::v4i32, Expand);
+  setOperationAction(ISD::SRA, MVT::v2i32, Expand);
 
   setOperationAction(ISD::SUB, MVT::v2i32, Expand);
   setOperationAction(ISD::SUB, MVT::v4i32, Expand);

diff --git a/test/CodeGen/R600/sra.ll b/test/CodeGen/R600/sra.ll
index 972542d346f499caff3422b3638e93f13d4173ad..7c5cc754cb5124826525931731e73fe14b8d858c 100644 (file)
--- a/test/CodeGen/R600/sra.ll
+++ b/test/CodeGen/R600/sra.ll
@@ -1,12 +1,39 @@
-; 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
 
-; CHECK: @ashr_v4i32
-; CHECK: ASHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-; CHECK: ASHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-; CHECK: ASHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-; CHECK: ASHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: @ashr_v2i32
+;EG-CHECK: ASHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: ASHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-define void @ashr_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b) {
+;SI-CHECK: @ashr_v2i32
+;SI-CHECK: V_ASHR_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_ASHR_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+
+define void @ashr_v2i32(<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 = ashr <2 x i32> %a, %b
+  store <2 x i32> %result, <2 x i32> addrspace(1)* %out
+  ret void
+}
+
+;EG-CHECK: @ashr_v4i32
+;EG-CHECK: ASHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: ASHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: ASHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: ASHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+
+;SI-CHECK: @ashr_v4i32
+;SI-CHECK: V_ASHR_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_ASHR_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_ASHR_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_ASHR_I32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+
+define void @ashr_v4i32(<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
   %result = ashr <4 x i32> %a, %b
   store <4 x i32> %result, <4 x i32> addrspace(1)* %out
   ret void