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/AMDGPU/schedule-kernel-arg-loads.ll

51 lines
3.1 KiB
LLVM
Raw Normal View History

AMDGPU: Define priorities for register classes Allocating larger register classes first should give better allocation results (and more importantly for myself, make the lit tests more stable with respect to scheduler changes). Patch by Matthias Braun llvm-svn: 270312
2016-05-21 11:55:07 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=SI -check-prefix=GCN %s
Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=VI -check-prefix=GCN %s
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
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: {{^}}cluster_arg_loads:
AMDGPU/SI: Use the hazard recognizer to break SMEM soft clauses Summary: Add support for detecting hazards in SMEM soft clauses, so that we only break the clauses when necessary, either by adding s_nop or re-ordering other alu instructions. Reviewers: arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18870 llvm-svn: 268260
2016-05-03 01:39:06 +08:00
; FIXME: Due to changes in the load clustering heuristics. We no longer
; cluster all argument loads together on SI.
AMDGPU/SI: Limit load clustering to 16 bytes instead of 4 instructions Summary: This helps prevent load clustering from drastically increasing register pressure by trying to cluster 4 SMRDx8 loads together. The limit of 16 bytes was chosen, because it seems like that was the original intent of setting the limit to 4 instructions, but more analysis could show that a different limit is better. This fixes yields small decreases in register usage with shader-db, but also helps avoid a large increase in register usage when lane mask tracking is enabled in the machine scheduler, because lane mask tracking enables more opportunities for load clustering. shader-db stats: 2379 shaders in 477 tests Totals: SGPRS: 49744 -> 48600 (-2.30 %) VGPRS: 34120 -> 34076 (-0.13 %) Code Size: 1282888 -> 1283184 (0.02 %) bytes LDS: 28 -> 28 (0.00 %) blocks Scratch: 495616 -> 492544 (-0.62 %) bytes per wave Max Waves: 6843 -> 6853 (0.15 %) Wait states: 0 -> 0 (0.00 %) Reviewers: nhaehnle, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18451 llvm-svn: 264589
2016-03-29 00:10:13 +08:00
; SI: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd
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: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x9
; SI-NEXT: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xb
AMDGPU: Define a schedule class for COPY. COPY was lacking a scheduling class, define it to avoid regressions in the upcoming change to the bidirectional MachineScheduler. Approved by tstellar on IRC. Differential Revision: http://reviews.llvm.org/D21540 llvm-svn: 273751
2016-06-25 07:52:11 +08:00
; SI-NEXT: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0xe
AMDGPU/SI: Limit load clustering to 16 bytes instead of 4 instructions Summary: This helps prevent load clustering from drastically increasing register pressure by trying to cluster 4 SMRDx8 loads together. The limit of 16 bytes was chosen, because it seems like that was the original intent of setting the limit to 4 instructions, but more analysis could show that a different limit is better. This fixes yields small decreases in register usage with shader-db, but also helps avoid a large increase in register usage when lane mask tracking is enabled in the machine scheduler, because lane mask tracking enables more opportunities for load clustering. shader-db stats: 2379 shaders in 477 tests Totals: SGPRS: 49744 -> 48600 (-2.30 %) VGPRS: 34120 -> 34076 (-0.13 %) Code Size: 1282888 -> 1283184 (0.02 %) bytes LDS: 28 -> 28 (0.00 %) blocks Scratch: 495616 -> 492544 (-0.62 %) bytes per wave Max Waves: 6843 -> 6853 (0.15 %) Wait states: 0 -> 0 (0.00 %) Reviewers: nhaehnle, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18451 llvm-svn: 264589
2016-03-29 00:10:13 +08:00
; VI: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x34
AMDGPU: Define priorities for register classes Allocating larger register classes first should give better allocation results (and more importantly for myself, make the lit tests more stable with respect to scheduler changes). Patch by Matthias Braun llvm-svn: 270312
2016-05-21 11:55:07 +08:00
; VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x24
; VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x2c
AMDGPU: Define a schedule class for COPY. COPY was lacking a scheduling class, define it to avoid regressions in the upcoming change to the bidirectional MachineScheduler. Approved by tstellar on IRC. Differential Revision: http://reviews.llvm.org/D21540 llvm-svn: 273751
2016-06-25 07:52:11 +08:00
; VI: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x38
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 @cluster_arg_loads(i32 addrspace(1)* %out0, i32 addrspace(1)* %out1, i32 %x, i32 %y) nounwind {
store i32 %x, i32 addrspace(1)* %out0, align 4
store i32 %y, i32 addrspace(1)* %out1, align 4
ret void
}
R600/SI: Fix crash in SIInstrInfo::areLoadsFromSameBasePtr() This function assumed that SMRD instructions always have immediate offsets, which is not always the case. llvm-svn: 232957
2015-03-24 00:06:01 +08:00
; Test for a crash in SIInstrInfo::areLoadsFromSameBasePtr() when
; s_load_dwordx2 has a register offset
; FUNC-LABEL: @same_base_ptr_crash
; GCN: s_load_dwordx2
; GCN: s_load_dwordx2
; GCN: s_load_dwordx2
; GCN: s_endpgm
define void @same_base_ptr_crash(i64 addrspace(1)* %out,
i64 %arg0, i64 %arg1, i64 %arg2, i64 %arg3, i64 %arg4, i64 %arg5, i64 %arg6, i64 %arg7,
i64 %arg8, i64 %arg9, i64 %arg10, i64 %arg11, i64 %arg12, i64 %arg13, i64 %arg14, i64 %arg15,
i64 %arg16, i64 %arg17, i64 %arg18, i64 %arg19, i64 %arg20, i64 %arg21, i64 %arg22, i64 %arg23,
i64 %arg24, i64 %arg25, i64 %arg26, i64 %arg27, i64 %arg28, i64 %arg29, i64 %arg30, i64 %arg31,
i64 %arg32, i64 %arg33, i64 %arg34, i64 %arg35, i64 %arg36, i64 %arg37, i64 %arg38, i64 %arg39,
i64 %arg40, i64 %arg41, i64 %arg42, i64 %arg43, i64 %arg44, i64 %arg45, i64 %arg46, i64 %arg47,
i64 %arg48, i64 %arg49, i64 %arg50, i64 %arg51, i64 %arg52, i64 %arg53, i64 %arg54, i64 %arg55,
i64 %arg56, i64 %arg57, i64 %arg58, i64 %arg59, i64 %arg60, i64 %arg61, i64 %arg62, i64 %arg63,
i64 %arg64, i64 %arg65, i64 %arg66, i64 %arg67, i64 %arg68, i64 %arg69, i64 %arg70, i64 %arg71,
i64 %arg72, i64 %arg73, i64 %arg74, i64 %arg75, i64 %arg76, i64 %arg77, i64 %arg78, i64 %arg79,
i64 %arg80, i64 %arg81, i64 %arg82, i64 %arg83, i64 %arg84, i64 %arg85, i64 %arg86, i64 %arg87,
i64 %arg88, i64 %arg89, i64 %arg90, i64 %arg91, i64 %arg92, i64 %arg93, i64 %arg94, i64 %arg95,
i64 %arg96, i64 %arg97, i64 %arg98, i64 %arg99, i64 %arg100, i64 %arg101, i64 %arg102, i64 %arg103,
i64 %arg104, i64 %arg105, i64 %arg106, i64 %arg107, i64 %arg108, i64 %arg109, i64 %arg110, i64 %arg111,
i64 %arg112, i64 %arg113, i64 %arg114, i64 %arg115, i64 %arg116, i64 %arg117, i64 %arg118, i64 %arg119,
i64 %arg120, i64 %arg121, i64 %arg122, i64 %arg123, i64 %arg124, i64 %arg125, i64 %arg126) {
entry:
%value = add i64 %arg125, %arg126
store i64 %value, i64 addrspace(1)* %out, align 8
ret void
}