maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/R600/llvm.AMDGPU.umad24.ll

39 lines
1.9 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. llvm-svn: 225277
2015-01-07 02:00:21 +08:00
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
R600: Expand mad24 for GPUs without it llvm-svn: 209457
2014-05-23 02:00:20 +08:00
; 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 llvm-svn: 209456
2014-05-23 02:00:15 +08:00
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. llvm-svn: 221910
2014-11-14 03:26:47 +08:00
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
R600: Add intrinsics for mad24 llvm-svn: 209456
2014-05-23 02:00:15 +08:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; 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 llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: v_mad_u32_u24
R600: Expand mad24 for GPUs without it llvm-svn: 209457
2014-05-23 02:00:20 +08:00
; EG: MULADD_UINT24
; R600: MULLO_UINT
; R600: ADD_INT
R600: Add intrinsics for mad24 llvm-svn: 209456
2014-05-23 02:00:15 +08:00
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. llvm-svn: 221910
2014-11-14 03:26:47 +08:00
; 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. llvm-svn: 223194
2014-12-03 11:12:13 +08:00
; 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. llvm-svn: 221910
2014-11-14 03:26:47 +08:00
; 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
}