6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-27 13:30:05 +00:00
Code Issues Projects Releases Wiki Activity

R600: Enable vector fpow.

Browse Source 
The OpenCL specs say: "The vector versions of the math functions operate
component-wise. The description is per-component."

Patch by: Jan Vesely

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200773 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tom Stellard 2014-02-04 17:18:37 +00:00
parent efb6bb6863
commit 4ee42eaec9
2 changed files with 26 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/Target/R600/AMDGPUISelLowering.cpp
View File

@ -185,6 +185,7 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(TargetMachine &TM) :
setOperationAction(ISD::FABS, VT, Expand);
setOperationAction(ISD::FADD, VT, Expand);
setOperationAction(ISD::FDIV, VT, Expand);
setOperationAction(ISD::FPOW, VT, Expand);
setOperationAction(ISD::FFLOOR, VT, Expand);
setOperationAction(ISD::FTRUNC, VT, Expand);
setOperationAction(ISD::FMUL, VT, Expand);

29
test/CodeGen/R600/llvm.pow.ll
View File

@ -1,10 +1,11 @@
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
;CHECK: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL NON-IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}}
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
;CHECK-LABEL: test1:
;CHECK: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
;CHECK-NEXT: MUL NON-IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
define void @test(<4 x float> inreg %reg0) #0 {
define void @test1(<4 x float> inreg %reg0) #0 {
%r0 = extractelement <4 x float> %reg0, i32 0
%r1 = extractelement <4 x float> %reg0, i32 1
%r2 = call float @llvm.pow.f32( float %r0, float %r1)
@ -13,7 +14,27 @@ define void @test(<4 x float> inreg %reg0) #0 {
ret void
}
;CHECK-LABEL: test2:
;CHECK: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
;CHECK-NEXT: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
;CHECK-NEXT: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
;CHECK-NEXT: LOG_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}},
;CHECK-NEXT: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], PS}},
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
;CHECK-NEXT: EXP_IEEE * T{{[0-9]+\.[XYZW], PV\.[XYZW]}},
define void @test2(<4 x float> inreg %reg0, <4 x float> inreg %reg1) #0 {
%vec = call <4 x float> @llvm.pow.v4f32( <4 x float> %reg0, <4 x float> %reg1)
call void @llvm.R600.store.swizzle(<4 x float> %vec, i32 0, i32 0)
ret void
}
declare float @llvm.pow.f32(float ,float ) readonly
declare <4 x float> @llvm.pow.v4f32(<4 x float> ,<4 x float> ) readonly
declare void @llvm.R600.store.swizzle(<4 x float>, i32, i32)
attributes #0 = { "ShaderType"="0" }