diff options
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/lib/Target/R600/SIISelLowering.cpp | 3 | ||||
| -rw-r--r-- | llvm/test/CodeGen/R600/shl.ll | 41 |
2 files changed, 37 insertions, 7 deletions
diff --git a/llvm/lib/Target/R600/SIISelLowering.cpp b/llvm/lib/Target/R600/SIISelLowering.cpp index 30a7de534d9..515c7a4f82f 100644 --- a/llvm/lib/Target/R600/SIISelLowering.cpp +++ b/llvm/lib/Target/R600/SIISelLowering.cpp @@ -77,6 +77,9 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) : 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); diff --git a/llvm/test/CodeGen/R600/shl.ll b/llvm/test/CodeGen/R600/shl.ll index db970e95c7a..d99e325af8f 100644 --- a/llvm/test/CodeGen/R600/shl.ll +++ b/llvm/test/CodeGen/R600/shl.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: @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 |
