6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-25 14:32:53 +00:00
Code Issues Projects Releases Wiki Activity
18c8166405
llvm-6502/test/CodeGen/R600/rsq.ll

75 lines
2.9 KiB
LLVM
Raw Normal View History

R600/SI: Add a stub GCNTargetMachine This is equivalent to the AMDGPUTargetMachine now, but it is the starting point for separating R600 and GCN functionality into separate targets. It is recommened that users start using the gcn triple for GCN-based GPUs, because using the r600 triple for these GPUs will be deprecated in the future. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225277 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-06 18:00:21 +00:00
; RUN: llc -march=amdgcn -mcpu=SI -mattr=-fp32-denormals -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=SI-UNSAFE -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=SI -mattr=-fp32-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=SI-SAFE -check-prefix=SI %s
R600/SI: Match rsq instructions git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210226 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-05 00:15:55 +00:00
R600: Implement getRsqrtEstimate Only do for f32 since I'm unclear on both what this is expecting for the refinement steps in terms of accuracy, and what f64 instruction actually provides. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225827 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-13 20:53:18 +00:00
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
R600/SI: Match rsq instructions git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210226 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-05 00:15:55 +00:00
declare float @llvm.sqrt.f32(float) nounwind readnone
declare double @llvm.sqrt.f64(double) nounwind readnone
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}rsq_f32:
R600/SI: Change all instruction assembly names to lowercase. 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
2014-11-05 14:50:53 +00:00
; SI: v_rsq_f32_e32
; SI: s_endpgm
R600/SI: Match rsq instructions git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210226 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-05 00:15:55 +00:00
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
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}rsq_f64:
R600/SI: Change all instruction assembly names to lowercase. 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
2014-11-05 14:50:53 +00:00
; SI-UNSAFE: v_rsq_f64_e32
; SI-SAFE: v_sqrt_f64_e32
; SI: s_endpgm
R600/SI: Match rsq instructions git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210226 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-05 00:15:55 +00:00
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
}
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217789 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-15 17:15:02 +00:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}rsq_f32_sgpr:
R600/SI: Change all instruction assembly names to lowercase. 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
2014-11-05 14:50:53 +00:00
; SI: v_rsq_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
; SI: s_endpgm
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217789 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-15 17:15:02 +00:00
define void @rsq_f32_sgpr(float addrspace(1)* noalias %out, float %val) nounwind {
%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
}
R600: Implement getRsqrtEstimate Only do for f32 since I'm unclear on both what this is expecting for the refinement steps in terms of accuracy, and what f64 instruction actually provides. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225827 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-13 20:53:18 +00:00
; Recognize that this is rsqrt(a) * rcp(b) * c,
; not 1 / ( 1 / sqrt(a)) * rcp(b) * c.
; SI-LABEL: @rsqrt_fmul
; SI-DAG: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
; SI-DAG: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
; SI-DAG: buffer_load_dword [[C:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:8
; SI-UNSAFE-DAG: v_rsq_f32_e32 [[RSQA:v[0-9]+]], [[A]]
; SI-UNSAFE-DAG: v_rcp_f32_e32 [[RCPB:v[0-9]+]], [[B]]
; SI-UNSAFE-DAG: v_mul_f32_e32 [[TMP:v[0-9]+]], [[RCPB]], [[RSQA]]
; SI-UNSAFE: v_mul_f32_e32 [[RESULT:v[0-9]+]], [[TMP]], [[C]]
; SI-UNSAFE: buffer_store_dword [[RESULT]]
; SI-SAFE-NOT: v_rsq_f32
; SI: s_endpgm
define void @rsqrt_fmul(float addrspace(1)* %out, float addrspace(1)* %in) {
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
%out.gep = getelementptr float addrspace(1)* %out, i32 %tid
%gep.0 = getelementptr float addrspace(1)* %in, i32 %tid
%gep.1 = getelementptr float addrspace(1)* %gep.0, i32 1
%gep.2 = getelementptr float addrspace(1)* %gep.0, i32 2
%a = load float addrspace(1)* %gep.0
%b = load float addrspace(1)* %gep.1
%c = load float addrspace(1)* %gep.2
%x = call float @llvm.sqrt.f32(float %a)
%y = fmul float %x, %b
%z = fdiv float %c, %y
store float %z, float addrspace(1)* %out.gep
ret void
}
Reference in New Issue Copy Permalink