6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-29 10:32:47 +00:00
Code Issues Projects Releases Wiki Activity
6f44989d39
llvm-6502/test/CodeGen/R600/llvm.AMDGPU.umad24.ll

39 lines
1.9 KiB
LLVM
Raw Normal View History

R600: Add intrinsics for mad24 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209456 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-22 18:00:15 +00:00
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
R600: Expand mad24 for GPUs without it git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209457 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-22 18:00:20 +00:00
; RUN: llc -march=r600 -mcpu=cayman -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; XUN: llc -march=r600 -mcpu=r600 -verify-machineinstrs < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
; XUN: llc -march=r600 -mcpu=rv770 -verify-machineinstrs < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
R600: Add intrinsics for mad24 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209456 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-22 18:00:15 +00:00
declare i32 @llvm.AMDGPU.umad24(i32, i32, i32) nounwind readnone
R600/SI: Allow commuting some 3 op instructions e.g. v_mad_f32 a, b, c -> v_mad_f32 b, a, c This simplifies matching v_madmk_f32. This looks somewhat surprising, but it appears to be OK to do this. We can commute src0 and src1 in all of these instructions, and that's all that appears to matter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221910 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-13 19:26:47 +00:00
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
R600: Add intrinsics for mad24 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209456 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-22 18:00:15 +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
; FUNC-LABEL: {{^}}test_umad24:
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_mad_u32_u24
R600: Expand mad24 for GPUs without it git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209457 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-22 18:00:20 +00:00
; EG: MULADD_UINT24
; R600: MULLO_UINT
; R600: ADD_INT
R600: Add intrinsics for mad24 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209456 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-22 18:00:15 +00:00
define void @test_umad24(i32 addrspace(1)* %out, i32 %src0, i32 %src1, i32 %src2) nounwind {
%mad = call i32 @llvm.AMDGPU.umad24(i32 %src0, i32 %src1, i32 %src2) nounwind readnone
store i32 %mad, i32 addrspace(1)* %out, align 4
ret void
}
R600/SI: Allow commuting some 3 op instructions e.g. v_mad_f32 a, b, c -> v_mad_f32 b, a, c This simplifies matching v_madmk_f32. This looks somewhat surprising, but it appears to be OK to do this. We can commute src0 and src1 in all of these instructions, and that's all that appears to matter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221910 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-13 19:26:47 +00:00
; FUNC-LABEL: {{^}}commute_umad24:
; SI-DAG: buffer_load_dword [[SRC0:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
R600/SI: Change mubuf offsets to print as decimal This matches SC's behavior. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223194 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-03 03:12:13 +00:00
; SI-DAG: buffer_load_dword [[SRC2:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
R600/SI: Allow commuting some 3 op instructions e.g. v_mad_f32 a, b, c -> v_mad_f32 b, a, c This simplifies matching v_madmk_f32. This looks somewhat surprising, but it appears to be OK to do this. We can commute src0 and src1 in all of these instructions, and that's all that appears to matter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221910 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-13 19:26:47 +00:00
; SI: v_mad_u32_u24 [[RESULT:v[0-9]+]], 4, [[SRC0]], [[SRC2]]
; SI: buffer_store_dword [[RESULT]]
define void @commute_umad24(i32 addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
%out.gep = getelementptr i32 addrspace(1)* %out, i32 %tid
%src0.gep = getelementptr i32 addrspace(1)* %out, i32 %tid
%src2.gep = getelementptr i32 addrspace(1)* %src0.gep, i32 1
%src0 = load i32 addrspace(1)* %src0.gep, align 4
%src2 = load i32 addrspace(1)* %src2.gep, align 4
%mad = call i32 @llvm.AMDGPU.umad24(i32 %src0, i32 4, i32 %src2) nounwind readnone
store i32 %mad, i32 addrspace(1)* %out.gep, align 4
ret void
}
Reference in New Issue Copy Permalink