diff options
| author | Aaron Watry <awatry@gmail.com> | 2013-06-25 13:55:29 +0000 |
|---|---|---|
| committer | Aaron Watry <awatry@gmail.com> | 2013-06-25 13:55:29 +0000 |
| commit | b8ce77752b9654fa81f80d63a50a8d5c5b390c9a (patch) | |
| tree | 64480d8011a350dcb59926301f62359b87cc4a96 | |
| parent | 02ed261f7f7601f8ed5685345f3542b5120bcbf0 (diff) | |
| download | external_llvm-b8ce77752b9654fa81f80d63a50a8d5c5b390c9a.zip external_llvm-b8ce77752b9654fa81f80d63a50a8d5c5b390c9a.tar.gz external_llvm-b8ce77752b9654fa81f80d63a50a8d5c5b390c9a.tar.bz2 | |
R600/SI: Expand or 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@184839 91177308-0d34-0410-b5e6-96231b3b80d8
| -rw-r--r-- | lib/Target/R600/SIISelLowering.cpp | 3 | ||||
| -rw-r--r-- | test/CodeGen/R600/or.ll | 41 |
2 files changed, 37 insertions, 7 deletions
diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp index cb80e5e..30a7de5 100644 --- a/lib/Target/R600/SIISelLowering.cpp +++ b/lib/Target/R600/SIISelLowering.cpp @@ -74,6 +74,9 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) : setOperationAction(ISD::MUL, MVT::v2i32, Expand); setOperationAction(ISD::MUL, MVT::v4i32, Expand); + setOperationAction(ISD::OR, MVT::v2i32, Expand); + setOperationAction(ISD::OR, MVT::v4i32, Expand); + setOperationAction(ISD::SUB, MVT::v2i32, Expand); setOperationAction(ISD::SUB, MVT::v4i32, Expand); diff --git a/test/CodeGen/R600/or.ll b/test/CodeGen/R600/or.ll index b0dbb02..4a4e892 100644 --- a/test/CodeGen/R600/or.ll +++ b/test/CodeGen/R600/or.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: @or_v4i32 -; CHECK: OR_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -; CHECK: OR_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -; CHECK: OR_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -; CHECK: OR_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +; EG-CHECK: @or_v2i32 +; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} -define void @or_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b) { +;SI-CHECK: @or_v2i32 +;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} + +define void @or_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 = or <2 x i32> %a, %b + store <2 x i32> %result, <2 x i32> addrspace(1)* %out + ret void +} + +; EG-CHECK: @or_v4i32 +; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +; EG-CHECK: OR_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} + +;SI-CHECK: @or_v4i32 +;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} +;SI-CHECK: V_OR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}} + +define void @or_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 = or <4 x i32> %a, %b store <4 x i32> %result, <4 x i32> addrspace(1)* %out ret void |