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/wait.ll

46 lines
2.3 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 -strict-whitespace %s
R600/SI: Enable all tests that pass on VI without changes llvm-svn: 227214
2015-01-28 01:27:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -strict-whitespace %s
R600: improve dump of S_WAITCNT llvm-svn: 192557
2013-10-14 01:56:28 +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
; CHECK-LABEL: {{^}}main:
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
; CHECK: s_load_dwordx4
; CHECK: s_load_dwordx4
R600/SI: Define a schedule model and enable the generic machine scheduler The schedule model is not complete yet, and could be improved. llvm-svn: 227461
2015-01-30 00:55:25 +08:00
; CHECK: s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
; CHECK: s_endpgm
R600/SI: Implement areLoadsFromSameBasePtr This currently has a noticable effect on the kernel argument loads. LDS and global loads are more problematic, I think because of how copies are currently inserted to ensure that the address is a VGPR. llvm-svn: 214942
2014-08-06 08:29:43 +08:00
define void @main(<16 x i8> addrspace(2)* inreg %arg, <16 x i8> addrspace(2)* inreg %arg1, <32 x i8> addrspace(2)* inreg %arg2, <16 x i8> addrspace(2)* inreg %arg3, <16 x i8> addrspace(2)* inreg %arg4, i32 inreg %arg5, i32 %arg6, i32 %arg7, i32 %arg8, i32 %arg9, float addrspace(2)* inreg %constptr) #0 {
R600: improve dump of S_WAITCNT llvm-svn: 192557
2013-10-14 01:56:28 +08:00
main_body:
R600/SI: Implement areLoadsFromSameBasePtr This currently has a noticable effect on the kernel argument loads. LDS and global loads are more problematic, I think because of how copies are currently inserted to ensure that the address is a VGPR. llvm-svn: 214942
2014-08-06 08:29:43 +08:00
%tmp = getelementptr <16 x i8> addrspace(2)* %arg3, i32 0
%tmp10 = load <16 x i8> addrspace(2)* %tmp, !tbaa !0
%tmp11 = call <4 x float> @llvm.SI.vs.load.input(<16 x i8> %tmp10, i32 0, i32 %arg6)
%tmp12 = extractelement <4 x float> %tmp11, i32 0
%tmp13 = extractelement <4 x float> %tmp11, i32 1
call void @llvm.AMDGPU.barrier.global() #1
%tmp14 = extractelement <4 x float> %tmp11, i32 2
; %tmp15 = extractelement <4 x float> %tmp11, i32 3
%tmp15 = load float addrspace(2)* %constptr, align 4 ; Force waiting for expcnt and lgkmcnt
%tmp16 = getelementptr <16 x i8> addrspace(2)* %arg3, i32 1
%tmp17 = load <16 x i8> addrspace(2)* %tmp16, !tbaa !0
%tmp18 = call <4 x float> @llvm.SI.vs.load.input(<16 x i8> %tmp17, i32 0, i32 %arg6)
%tmp19 = extractelement <4 x float> %tmp18, i32 0
%tmp20 = extractelement <4 x float> %tmp18, i32 1
%tmp21 = extractelement <4 x float> %tmp18, i32 2
%tmp22 = extractelement <4 x float> %tmp18, i32 3
call void @llvm.SI.export(i32 15, i32 0, i32 0, i32 32, i32 0, float %tmp19, float %tmp20, float %tmp21, float %tmp22)
call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %tmp12, float %tmp13, float %tmp14, float %tmp15)
R600: improve dump of S_WAITCNT llvm-svn: 192557
2013-10-14 01:56:28 +08:00
ret void
}
R600/SI: Implement areLoadsFromSameBasePtr This currently has a noticable effect on the kernel argument loads. LDS and global loads are more problematic, I think because of how copies are currently inserted to ensure that the address is a VGPR. llvm-svn: 214942
2014-08-06 08:29:43 +08:00
; Function Attrs: noduplicate nounwind
declare void @llvm.AMDGPU.barrier.global() #1
R600: improve dump of S_WAITCNT llvm-svn: 192557
2013-10-14 01:56:28 +08:00
; Function Attrs: nounwind readnone
R600/SI: Implement areLoadsFromSameBasePtr This currently has a noticable effect on the kernel argument loads. LDS and global loads are more problematic, I think because of how copies are currently inserted to ensure that the address is a VGPR. llvm-svn: 214942
2014-08-06 08:29:43 +08:00
declare <4 x float> @llvm.SI.vs.load.input(<16 x i8>, i32, i32) #2
R600: improve dump of S_WAITCNT llvm-svn: 192557
2013-10-14 01:56:28 +08:00
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
attributes #0 = { "ShaderType"="1" }
R600/SI: Implement areLoadsFromSameBasePtr This currently has a noticable effect on the kernel argument loads. LDS and global loads are more problematic, I think because of how copies are currently inserted to ensure that the address is a VGPR. llvm-svn: 214942
2014-08-06 08:29:43 +08:00
attributes #1 = { noduplicate nounwind }
attributes #2 = { nounwind readnone }
R600: improve dump of S_WAITCNT llvm-svn: 192557
2013-10-14 01:56:28 +08:00
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!0 = !{!1, !1, i64 0, i32 1}
!1 = !{!"const", null}