[llvm] r184840 - R600/SI: Expand shl of v2i32/v4i32 for SI

[Aaron Watry]

Author: awatry
Date: Tue Jun 25 08:55:32 2013
New Revision: 184840

URL: http://llvm.org/viewvc/llvm-project?rev=184840&view=rev
Log:
R600/SI: Expand shl of v2i32/v4i32 for SI

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

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

Modified:
    llvm/trunk/lib/Target/R600/SIISelLowering.cpp
    llvm/trunk/test/CodeGen/R600/shl.ll

Modified: llvm/trunk/lib/Target/R600/SIISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/R600/SIISelLowering.cpp?rev=184840&r1=184839&r2=184840&view=diff
==============================================================================
--- llvm/trunk/lib/Target/R600/SIISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/R600/SIISelLowering.cpp Tue Jun 25 08:55:32 2013
@@ -77,6 +77,9 @@ SITargetLowering::SITargetLowering(Targe
   setOperationAction(ISD::OR, MVT::v2i32, Expand);
   setOperationAction(ISD::OR, MVT::v4i32, Expand);
 
+  setOperationAction(ISD::SHL, MVT::v2i32, Expand);
+  setOperationAction(ISD::SHL, MVT::v4i32, Expand);
+
   setOperationAction(ISD::SUB, MVT::v2i32, Expand);
   setOperationAction(ISD::SUB, MVT::v4i32, Expand);
 

Modified: llvm/trunk/test/CodeGen/R600/shl.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/R600/shl.ll?rev=184840&r1=184839&r2=184840&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/R600/shl.ll (original)
+++ llvm/trunk/test/CodeGen/R600/shl.ll Tue Jun 25 08:55:32 2013
@@ -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: @shl_v4i32
-; CHECK: LSHL * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-; CHECK: LSHL * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-; CHECK: LSHL * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-; CHECK: LSHL * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: @shl_v2i32
+;EG-CHECK: LSHL {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: LSHL {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-define void @shl_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b) {
+;SI-CHECK: @shl_v2i32
+;SI-CHECK: V_LSHL_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_LSHL_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+
+define void @shl_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 = shl <2 x i32> %a, %b
+  store <2 x i32> %result, <2 x i32> addrspace(1)* %out
+  ret void
+}
+
+;EG-CHECK: @shl_v4i32
+;EG-CHECK: LSHL {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: LSHL {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: LSHL {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG-CHECK: LSHL {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+
+;SI-CHECK: @shl_v4i32
+;SI-CHECK: V_LSHL_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_LSHL_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_LSHL_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+;SI-CHECK: V_LSHL_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
+
+define void @shl_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 = shl <4 x i32> %a, %b
   store <4 x i32> %result, <4 x i32> addrspace(1)* %out
   ret void