diff options
| author | Aaron Watry <awatry@gmail.com> | 2013-06-25 13:55:37 +0000 |
|---|---|---|
| committer | Aaron Watry <awatry@gmail.com> | 2013-06-25 13:55:37 +0000 |
| commit | 61de9f83cb67a9738fa146e2b4542332aabee019 (patch) | |
| tree | ce5940c4b523d7e5dc34d3c5377fe2a86116a6d9 | |
| parent | 60e6dacd1c21eba75599a294fe37a6072c37604f (diff) | |
| download | llvm-61de9f83cb67a9738fa146e2b4542332aabee019.tar.gz llvm-61de9f83cb67a9738fa146e2b4542332aabee019.tar.bz2 llvm-61de9f83cb67a9738fa146e2b4542332aabee019.tar.xz | |
R600/SI: Expand srl 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@184841 91177308-0d34-0410-b5e6-96231b3b80d8
| -rw-r--r-- | lib/Target/R600/SIISelLowering.cpp | 2 | ||||
| -rw-r--r-- | test/CodeGen/R600/srl.ll | 42 |
2 files changed, 37 insertions, 7 deletions
diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp index 515c7a4f82..4219825ecd 100644 --- a/lib/Target/R600/SIISelLowering.cpp +++ b/lib/Target/R600/SIISelLowering.cpp @@ -79,6 +79,8 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) : setOperationAction(ISD::SHL, MVT::v2i32, Expand); setOperationAction(ISD::SHL, MVT::v4i32, Expand); + setOperationAction(ISD::SRL, MVT::v4i32, Expand); + setOperationAction(ISD::SRL, MVT::v2i32, Expand); setOperationAction(ISD::SUB, MVT::v2i32, Expand); setOperationAction(ISD::SUB, MVT::v4i32, Expand); diff --git a/test/CodeGen/R600/srl.ll b/test/CodeGen/R600/srl.ll index 5f63600b75..d1dcd7f9b2 100644 --- a/test/CodeGen/R600/srl.ll +++ b/test/CodeGen/R600/srl.ll @@ -1,12 +1,40 @@ -; 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: @lshr_v4i32 -; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +;EG-CHECK: @lshr_v2i32 +;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -define void @lshr_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b) { +;SI-CHECK: @lshr_v2i32 +;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} + +define void @lshr_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 = lshr <2 x i32> %a, %b + store <2 x i32> %result, <2 x i32> addrspace(1)* %out + ret void +} + + +;EG-CHECK: @lshr_v4i32 +;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} + +;SI-CHECK: @lshr_v4i32 +;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} + +define void @lshr_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 = lshr <4 x i32> %a, %b store <4 x i32> %result, <4 x i32> addrspace(1)* %out ret void |