mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 19:29:22 +00:00
This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
99 lines
2.8 KiB
LLVM
99 lines
2.8 KiB
LLVM
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
|
|
|
|
|
|
; DAGCombiner will transform:
|
|
; (fabs (f32 bitcast (i32 a))) => (f32 bitcast (and (i32 a), 0x7FFFFFFF))
|
|
; unless isFabsFree returns true
|
|
|
|
; FUNC-LABEL: {{^}}fabs_fn_free:
|
|
; R600-NOT: AND
|
|
; R600: |PV.{{[XYZW]}}|
|
|
|
|
; SI: v_and_b32
|
|
|
|
define void @fabs_fn_free(float addrspace(1)* %out, i32 %in) {
|
|
%bc= bitcast i32 %in to float
|
|
%fabs = call float @fabs(float %bc)
|
|
store float %fabs, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_free:
|
|
; R600-NOT: AND
|
|
; R600: |PV.{{[XYZW]}}|
|
|
|
|
; SI: v_and_b32
|
|
|
|
define void @fabs_free(float addrspace(1)* %out, i32 %in) {
|
|
%bc= bitcast i32 %in to float
|
|
%fabs = call float @llvm.fabs.f32(float %bc)
|
|
store float %fabs, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_f32:
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
|
|
; SI: v_and_b32
|
|
define void @fabs_f32(float addrspace(1)* %out, float %in) {
|
|
%fabs = call float @llvm.fabs.f32(float %in)
|
|
store float %fabs, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_v2f32:
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
define void @fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) {
|
|
%fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
|
|
store <2 x float> %fabs, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_v4f32:
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
; R600: |{{(PV|T[0-9])\.[XYZW]}}|
|
|
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
define void @fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) {
|
|
%fabs = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in)
|
|
store <4 x float> %fabs, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}fabs_fn_fold:
|
|
; SI: s_load_dword [[ABS_VALUE:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xb
|
|
; SI-NOT: and
|
|
; SI: v_mul_f32_e64 v{{[0-9]+}}, |[[ABS_VALUE]]|, v{{[0-9]+}}
|
|
define void @fabs_fn_fold(float addrspace(1)* %out, float %in0, float %in1) {
|
|
%fabs = call float @fabs(float %in0)
|
|
%fmul = fmul float %fabs, %in1
|
|
store float %fmul, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}fabs_fold:
|
|
; SI: s_load_dword [[ABS_VALUE:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xb
|
|
; SI-NOT: and
|
|
; SI: v_mul_f32_e64 v{{[0-9]+}}, |[[ABS_VALUE]]|, v{{[0-9]+}}
|
|
define void @fabs_fold(float addrspace(1)* %out, float %in0, float %in1) {
|
|
%fabs = call float @llvm.fabs.f32(float %in0)
|
|
%fmul = fmul float %fabs, %in1
|
|
store float %fmul, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare float @fabs(float) readnone
|
|
declare float @llvm.fabs.f32(float) readnone
|
|
declare <2 x float> @llvm.fabs.v2f32(<2 x float>) readnone
|
|
declare <4 x float> @llvm.fabs.v4f32(<4 x float>) readnone
|