6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-04-11 16:37:42 +00:00
Code Issues Projects Releases Wiki Activity

R600/SI: Match rsq instructions

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210226 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Matt Arsenault 2014-06-05 00:15:55 +00:00
parent 1eb9c050ff
commit 798a829eca
2 changed files with 32 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/R600/SIInstructions.td
View File

@ -1017,12 +1017,16 @@ defm V_RSQ_LEGACY_F32 : VOP1_32 <
0x0000002d, "V_RSQ_LEGACY_F32",
[(set f32:$dst, (int_AMDGPU_rsq f32:$src0))]
>;
defm V_RSQ_F32 : VOP1_32 <0x0000002e, "V_RSQ_F32", []>;
defm V_RSQ_F32 : VOP1_32 <0x0000002e, "V_RSQ_F32",
[(set f32:$dst, (fdiv FP_ONE, (fsqrt f32:$src0)))]
>;
defm V_RCP_F64 : VOP1_64 <0x0000002f, "V_RCP_F64",
[(set f64:$dst, (fdiv FP_ONE, f64:$src0))]
>;
defm V_RCP_CLAMP_F64 : VOP1_64 <0x00000030, "V_RCP_CLAMP_F64", []>;
defm V_RSQ_F64 : VOP1_64 <0x00000031, "V_RSQ_F64", []>;
defm V_RSQ_F64 : VOP1_64 <0x00000031, "V_RSQ_F64",
[(set f64:$dst, (fdiv FP_ONE, (fsqrt f64:$src0)))]
>;
defm V_RSQ_CLAMP_F64 : VOP1_64 <0x00000032, "V_RSQ_CLAMP_F64", []>;
defm V_SQRT_F32 : VOP1_32 <0x00000033, "V_SQRT_F32",
[(set f32:$dst, (fsqrt f32:$src0))]

26
test/CodeGen/R600/rsq.ll Normal file
View File

@ -0,0 +1,26 @@
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
declare float @llvm.sqrt.f32(float) nounwind readnone
declare double @llvm.sqrt.f64(double) nounwind readnone
; SI-LABEL: @rsq_f32
; SI: V_RSQ_F32_e32
; SI: S_ENDPGM
define void @rsq_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
%val = load float addrspace(1)* %in, align 4
%sqrt = call float @llvm.sqrt.f32(float %val) nounwind readnone
%div = fdiv float 1.0, %sqrt
store float %div, float addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: @rsq_f64
; SI: V_RSQ_F64_e32
; SI: S_ENDPGM
define void @rsq_f64(double addrspace(1)* noalias %out, double addrspace(1)* noalias %in) nounwind {
%val = load double addrspace(1)* %in, align 4
%sqrt = call double @llvm.sqrt.f64(double %val) nounwind readnone
%div = fdiv double 1.0, %sqrt
store double %div, double addrspace(1)* %out, align 4
ret void
}