maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/DeadStoreElimination/multiblock-multipath.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

641 lines
17 KiB
LLVM
Raw Normal View History

[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
Recommit "[DSE] Switch to MemorySSA-backed DSE by default." After investigation by @asbirlea, the issue that caused the revert appears to be an issue in the original source, rather than a problem with the compiler. This patch enables MemorySSA DSE again. This reverts commit 915310bf14cbac58a81fd60e0fa9dc8d341108e2.
2020-10-16 15:42:18 +08:00
; RUN: opt < %s -basic-aa -dse -S | FileCheck %s
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
declare void @use(i32 *)
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; Tests where the pointer/object is accessible after the function returns.
define void @accessible_after_return_1(i32* noalias %P, i1 %c1) {
; CHECK-LABEL: @accessible_after_return_1(
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK-NEXT: br i1 [[C1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 3, i32* [[P]], align 4
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: ret void
;
store i32 1, i32* %P
br i1 %c1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
br label %bb5
bb2:
store i32 3, i32* %P
br label %bb5
bb5:
call void @use(i32* %P)
ret void
}
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @accessible_after_return_2(i32* noalias %P, i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @accessible_after_return_2(
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK: bb1:
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK: bb3:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 3, i32* [[P]], align 4
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb4:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 5, i32* [[P]], align 4
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: ret void
;
store i32 1, i32* %P
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
br i1 %c.1, label %bb1, label %bb2
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
bb1:
store i32 0, i32* %P
br label %bb5
bb2:
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
br i1 %c.2, label %bb3, label %bb4
[DSE,MSSA] Precommit additional tests for D73763.
2020-03-20 20:44:29 +08:00
bb3:
store i32 3, i32* %P
br label %bb5
bb4:
store i32 5, i32* %P
br label %bb5
bb5:
call void @use(i32* %P)
ret void
}
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; Cannot remove store in entry block because it is not overwritten on path
; entry->bb2->bb5.
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @accessible_after_return_3(i32* noalias %P, i1 %c1) {
; CHECK-LABEL: @accessible_after_return_3(
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 1, i32* [[P:%.*]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: ret void
;
store i32 1, i32* %P
br i1 %c1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
br label %bb5
bb2:
br label %bb5
bb5:
call void @use(i32* %P)
ret void
}
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; Cannot remove store in entry block because it is not overwritten on path
; entry->bb2->bb5.
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @accessible_after_return_4(i32* noalias %P, i1 %c1) {
; CHECK-LABEL: @accessible_after_return_4(
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 1, i32* [[P:%.*]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: ret void
;
store i32 1, i32* %P
br i1 %c1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
call void @use(i32* %P)
br label %bb5
bb2:
br label %bb5
bb5:
ret void
}
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; Cannot remove the store in entry, as it is not overwritten on all paths to an
; exit (patch including bb4).
define void @accessible_after_return5(i32* %P, i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @accessible_after_return5(
; CHECK-NEXT: entry:
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
; CHECK: bb2:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb3:
; CHECK-NEXT: store i32 2, i32* [[P]], align 4
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb4:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: ret void
;
entry:
store i32 0, i32* %P
br i1 %c.1, label %bb1, label %bb2
bb1:
br i1 %c.2, label %bb3, label %bb4
bb2:
store i32 1, i32* %P
br label %bb5
bb3:
store i32 2, i32* %P
br label %bb5
bb4:
br label %bb5
bb5:
ret void
}
; Can remove store in entry block, because it is overwritten before each return.
define void @accessible_after_return6(i32* %P, i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @accessible_after_return6(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
; CHECK: bb2:
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; CHECK-NEXT: store i32 1, i32* [[P:%.*]], align 4
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; CHECK-NEXT: ret void
; CHECK: bb3:
; CHECK-NEXT: store i32 2, i32* [[P]], align 4
; CHECK-NEXT: ret void
; CHECK: bb4:
; CHECK-NEXT: store i32 3, i32* [[P]], align 4
; CHECK-NEXT: ret void
;
entry:
store i32 0, i32* %P
br i1 %c.1, label %bb1, label %bb2
bb1:
br i1 %c.2, label %bb3, label %bb4
bb2:
store i32 1, i32* %P
ret void
bb3:
store i32 2, i32* %P
ret void
bb4:
store i32 3, i32* %P
ret void
}
; Can remove store in bb1, because it is overwritten along each path
; from bb1 to the exit.
define void @accessible_after_return7(i32* %P, i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @accessible_after_return7(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
; CHECK: bb3:
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; CHECK-NEXT: store i32 2, i32* [[P:%.*]], align 4
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb4:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: ret void
;
entry:
br i1 %c.1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
br i1 %c.2, label %bb3, label %bb4
bb3:
store i32 2, i32* %P
br label %bb5
bb4:
store i32 1, i32* %P
br label %bb5
bb2:
br label %bb5
bb5:
ret void
}
; Cannot remove store in entry block, because it is overwritten along each path to
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; the exit (entry->bb1->bb4->bb5).
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
define void @accessible_after_return8(i32* %P, i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @accessible_after_return8(
; CHECK-NEXT: entry:
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
; CHECK: bb2:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb3:
; CHECK-NEXT: store i32 2, i32* [[P]], align 4
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb4:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: ret void
;
entry:
store i32 0, i32* %P
br i1 %c.1, label %bb1, label %bb2
bb1:
br i1 %c.2, label %bb3, label %bb4
bb2:
store i32 1, i32* %P
br label %bb5
bb3:
store i32 2, i32* %P
br label %bb5
bb4:
br label %bb5
bb5:
ret void
}
; Make sure no stores are removed here. In particular, the store in if.then
; should not be removed.
define void @accessible_after_return9(i8* noalias %ptr) {
; CHECK-LABEL: @accessible_after_return9(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[C_0:%.*]] = call i1 @cond()
; CHECK-NEXT: br i1 [[C_0]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body:
; CHECK-NEXT: store i8 99, i8* [[PTR:%.*]], align 8
; CHECK-NEXT: [[C_1:%.*]] = call i1 @cond()
; CHECK-NEXT: br i1 [[C_1]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: store i8 20, i8* [[PTR]], align 8
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: [[C_2:%.*]] = call i1 @cond()
; CHECK-NEXT: br i1 [[C_2]], label [[IF_THEN10:%.*]], label [[FOR_INC:%.*]]
; CHECK: if.then10:
; CHECK-NEXT: store i8 0, i8* [[PTR]], align 8
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[C_3:%.*]] = call i1 @cond()
; CHECK-NEXT: br i1 [[C_3]], label [[FOR_BODY]], label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%c.0 = call i1 @cond()
br i1 %c.0, label %for.body, label %for.end
for.body:
store i8 99, i8* %ptr, align 8
%c.1 = call i1 @cond()
br i1 %c.1, label %if.end, label %if.then
if.then:
store i8 20, i8* %ptr, align 8
br label %if.end
if.end:
%c.2 = call i1 @cond()
br i1 %c.2, label %if.then10, label %for.inc
if.then10:
store i8 0, i8* %ptr, align 8
br label %for.inc
for.inc:
%c.3 = call i1 @cond()
br i1 %c.3, label %for.body, label %for.end
for.end:
ret void
}
[DSE,MSSA] Relax post-dom restriction for objs visible after return. This patch relaxes the post-dominance requirement for accesses to objects visible after the function returns. Instead of requiring the killing def to post-dominate the access to eliminate, the set of 'killing blocks' (= blocks that completely overwrite the original access) is collected. If all paths from the access to eliminate and an exit block go through a killing block, the access can be removed. To check this property, we first get the common post-dominator block for the killing blocks. If this block does not post-dominate the access block, there may be a path from DomAccess to an exit block not involving any killing block. Otherwise we have to check if there is a path from the DomAccess to the common post-dominator, that does not contain a killing block. If there is no such path, we can remove DomAccess. For this check, we start at the common post-dominator and then traverse the CFG backwards. Paths are terminated when we hit a killing block or a block that is not executed between DomAccess and a killing block according to the post-order numbering (if the post order number of a block is greater than the one of DomAccess, the block cannot be in in a path starting at DomAccess). This gives the following improvements on the total number of stores after DSE for MultiSource, SPEC2K, SPEC2006: Tests: 237 Same hash: 206 (filtered out) Remaining: 31 Metric: dse.NumRemainingStores Program base new100 diff test-suite...CFP2000/188.ammp/188.ammp.test 3624.00 3544.00 -2.2% test-suite...ch/g721/g721encode/encode.test 128.00 126.00 -1.6% test-suite.../Benchmarks/Olden/mst/mst.test 73.00 72.00 -1.4% test-suite...CFP2006/433.milc/433.milc.test 3202.00 3163.00 -1.2% test-suite...000/186.crafty/186.crafty.test 5062.00 5010.00 -1.0% test-suite...-typeset/consumer-typeset.test 40460.00 40248.00 -0.5% test-suite...Source/Benchmarks/sim/sim.test 642.00 639.00 -0.5% test-suite...nchmarks/McCat/09-vor/vor.test 642.00 644.00 0.3% test-suite...lications/sqlite3/sqlite3.test 35664.00 35563.00 -0.3% test-suite...T2000/300.twolf/300.twolf.test 7202.00 7184.00 -0.2% test-suite...lications/ClamAV/clamscan.test 19475.00 19444.00 -0.2% test-suite...INT2000/164.gzip/164.gzip.test 2199.00 2196.00 -0.1% test-suite...peg2/mpeg2dec/mpeg2decode.test 2380.00 2378.00 -0.1% test-suite.../Benchmarks/Bullet/bullet.test 39335.00 39309.00 -0.1% test-suite...:: External/Povray/povray.test 36951.00 36927.00 -0.1% test-suite...marks/7zip/7zip-benchmark.test 67396.00 67356.00 -0.1% test-suite...6/464.h264ref/464.h264ref.test 31497.00 31481.00 -0.1% test-suite...006/453.povray/453.povray.test 51441.00 51416.00 -0.0% test-suite...T2006/401.bzip2/401.bzip2.test 4450.00 4448.00 -0.0% test-suite...Applications/kimwitu++/kc.test 23481.00 23471.00 -0.0% test-suite...chmarks/MallocBench/gs/gs.test 6286.00 6284.00 -0.0% test-suite.../CINT2000/254.gap/254.gap.test 13719.00 13715.00 -0.0% test-suite.../Applications/SPASS/SPASS.test 30345.00 30338.00 -0.0% test-suite...006/450.soplex/450.soplex.test 15018.00 15016.00 -0.0% test-suite...ications/JM/lencod/lencod.test 27780.00 27777.00 -0.0% test-suite.../CINT2006/403.gcc/403.gcc.test 105285.00 105276.00 -0.0% There might be potential to pre-compute some of the information of which blocks are on the path to an exit for each block, but the overall benefit might be comparatively small. On the set of benchmarks, 15738 times out of 20322 we reach the CFG check, the CFG check is successful. The total number of iterations in the CFG check is 187810, so on average we need less than 10 steps in the check loop. Bumping the threshold in the loop from 50 to 150 gives a few small improvements, but I don't think they warrant such a big bump at the moment. This is all pending further tuning in the future. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: george.burgess.iv Differential Revision: https://reviews.llvm.org/D78932
2020-06-10 17:23:37 +08:00
; Cannot remove store in entry block because it is not overwritten on path
; entry->bb2->bb4. Also make sure we deal with dead exit blocks without
; crashing.
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
define void @accessible_after_return10_dead_block(i32* %P, i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @accessible_after_return10_dead_block(
; CHECK-NEXT: entry:
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
; CHECK: bb2:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: ret void
; CHECK: bb3:
; CHECK-NEXT: store i32 2, i32* [[P]], align 4
; CHECK-NEXT: ret void
; CHECK: bb4:
; CHECK-NEXT: ret void
; CHECK: bb5:
; CHECK-NEXT: ret void
;
entry:
store i32 0, i32* %P
br i1 %c.1, label %bb1, label %bb2
bb1:
br i1 %c.2, label %bb3, label %bb4
bb2:
store i32 1, i32* %P
ret void
bb3:
store i32 2, i32* %P
ret void
bb4:
ret void
bb5:
ret void
}
@linenum = external local_unnamed_addr global i32, align 4
define void @accessible_after_return11_loop() {
; CHECK-LABEL: @accessible_after_return11_loop(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY_I:%.*]]
; CHECK: for.body.i:
; CHECK-NEXT: [[C_1:%.*]] = call i1 @cond()
; CHECK-NEXT: br i1 [[C_1]], label [[FOR_BODY_I]], label [[INIT_PARSE_EXIT:%.*]]
; CHECK: init_parse.exit:
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull undef)
; CHECK-NEXT: store i32 0, i32* @linenum, align 4
; CHECK-NEXT: br label [[FOR_BODY_I20:%.*]]
; CHECK: for.body.i20:
; CHECK-NEXT: [[C_2:%.*]] = call i1 @cond()
; CHECK-NEXT: br i1 [[C_2]], label [[FOR_BODY_I20]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %for.body.i
for.body.i: ; preds = %for.body.i, %entry
%c.1 = call i1 @cond()
br i1 %c.1, label %for.body.i, label %init_parse.exit
init_parse.exit: ; preds = %for.body.i
store i32 0, i32* @linenum, align 4
call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull undef) #2
store i32 0, i32* @linenum, align 4
br label %for.body.i20
for.body.i20: ; preds = %for.body.i20, %init_parse.exit
%c.2 = call i1 @cond()
br i1 %c.2, label %for.body.i20, label %exit
exit:
ret void
}
declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
declare i1 @cond() readnone nounwind
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; Tests where the pointer/object is *NOT* accessible after the function returns.
[DSE] Lift post-dominance for objs not accessible in caller. We can eliminate MemoryDefs of objects not accessible after the function returns (e.g. alloca), if there are no reads between the MemoryDef and any function exits. We can stop traversing paths that completely overwrite the memory location of the MemoryDef. This patch was split off D73763. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: asbirlea, george.burgess.iv Differential Revision: https://reviews.llvm.org/D77736
2020-04-15 17:42:58 +08:00
; The store in the entry block can be eliminated, because it is overwritten
; on all paths to the exit.
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @alloca_1(i1 %c1) {
; CHECK-LABEL: @alloca_1(
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; CHECK-NEXT: [[P:%.*]] = alloca i32, align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 3, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: ret void
;
%P = alloca i32
store i32 1, i32* %P
br i1 %c1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
br label %bb5
bb2:
store i32 3, i32* %P
br label %bb5
bb5:
call void @use(i32* %P)
ret void
}
[DSE] Lift post-dominance for objs not accessible in caller. We can eliminate MemoryDefs of objects not accessible after the function returns (e.g. alloca), if there are no reads between the MemoryDef and any function exits. We can stop traversing paths that completely overwrite the memory location of the MemoryDef. This patch was split off D73763. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: asbirlea, george.burgess.iv Differential Revision: https://reviews.llvm.org/D77736
2020-04-15 17:42:58 +08:00
; The store in the entry block can be eliminated, because it is overwritten
; on all paths to the exit.
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @alloca_2(i1 %c.1, i1 %c.2) {
; CHECK-LABEL: @alloca_2(
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; CHECK-NEXT: [[P:%.*]] = alloca i32, align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C_1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br i1 [[C_2:%.*]], label [[BB3:%.*]], label [[BB4:%.*]]
; CHECK: bb3:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 3, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb4:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 5, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: ret void
;
%P = alloca i32
store i32 1, i32* %P
br i1 %c.1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
br label %bb5
bb2:
br i1 %c.2, label %bb3, label %bb4
bb3:
store i32 3, i32* %P
br label %bb5
bb4:
store i32 5, i32* %P
br label %bb5
bb5:
call void @use(i32* %P)
ret void
}
[DSE] Lift post-dominance for objs not accessible in caller. We can eliminate MemoryDefs of objects not accessible after the function returns (e.g. alloca), if there are no reads between the MemoryDef and any function exits. We can stop traversing paths that completely overwrite the memory location of the MemoryDef. This patch was split off D73763. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: asbirlea, george.burgess.iv Differential Revision: https://reviews.llvm.org/D77736
2020-04-15 17:42:58 +08:00
; The store in the entry block cannot be eliminated. There's a path from the
; first store to the read in bb5, where the location is not overwritten.
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @alloca_3(i1 %c1) {
; CHECK-LABEL: @alloca_3(
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; CHECK-NEXT: [[P:%.*]] = alloca i32, align 4
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: ret void
;
%P = alloca i32
store i32 1, i32* %P
br i1 %c1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
br label %bb5
bb2:
br label %bb5
bb5:
call void @use(i32* %P)
ret void
}
[DSE] Lift post-dominance for objs not accessible in caller. We can eliminate MemoryDefs of objects not accessible after the function returns (e.g. alloca), if there are no reads between the MemoryDef and any function exits. We can stop traversing paths that completely overwrite the memory location of the MemoryDef. This patch was split off D73763. Reviewers: dmgreen, bryant, asbirlea, Tyker, efriedma, george.burgess.iv Reviewed By: asbirlea, george.burgess.iv Differential Revision: https://reviews.llvm.org/D77736
2020-04-15 17:42:58 +08:00
; The store in the entry block can be eliminated, because it is overwritten
; before the use in bb1 and not read on other paths to the function exit. The
; object cannot be accessed by the caller.
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
define void @alloca_4(i1 %c1) {
; CHECK-LABEL: @alloca_4(
[DSE,MSSA] Add additional multiblock tests.
2020-04-27 22:46:12 +08:00
; CHECK-NEXT: [[P:%.*]] = alloca i32, align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: br i1 [[C1:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
StoreInst should store Align, not MaybeAlign This is D77454, except for stores. All the infrastructure work was done for loads, so the remaining changes necessary are relatively small. Differential Revision: https://reviews.llvm.org/D79968
2020-05-15 05:48:10 +08:00
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
[DSE,MSSA] Add additional test cases for multi-path elimination (NFC). This adds additional test cases for more scenarios and also with objects that are accessible after the functions return and allocas.
2020-04-08 22:23:58 +08:00
; CHECK-NEXT: call void @use(i32* [[P]])
; CHECK-NEXT: br label [[BB5:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB5]]
; CHECK: bb5:
; CHECK-NEXT: ret void
;
%P = alloca i32
store i32 1, i32* %P
br i1 %c1, label %bb1, label %bb2
bb1:
store i32 0, i32* %P
call void @use(i32* %P)
br label %bb5
bb2:
br label %bb5
bb5:
ret void
}
[DSE,MSSA] Fix location order in isOverwrite call. isOverwrite expects the later location as first argument and the earlier result later. The adjusted call is intended to check whether CC overwrites DefLoc.
2020-06-14 03:24:57 +08:00
%struct.blam.4 = type { %struct.bar.5, [4 x i8] }
%struct.bar.5 = type <{ i64, i64*, i32, i64 }>
; Make sure we do not eliminate the store in %bb.
define void @alloca_5(i1 %c) {
; CHECK-LABEL: @alloca_5(
; CHECK-NEXT: bb:
; CHECK-NEXT: [[TMP:%.*]] = alloca [[STRUCT_BLAM_4:%.*]], align 8
; CHECK-NEXT: [[TMP38:%.*]] = getelementptr inbounds [[STRUCT_BLAM_4]], %struct.blam.4* [[TMP]], i64 0, i32 0, i32 3
; CHECK-NEXT: [[TMP39:%.*]] = bitcast i64* [[TMP38]] to i64*
; CHECK-NEXT: store i64 0, i64* [[TMP39]], align 4
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB46:%.*]], label [[BB47:%.*]]
; CHECK: bb46:
; CHECK-NEXT: ret void
; CHECK: bb47:
; CHECK-NEXT: [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_BLAM_4]], %struct.blam.4* [[TMP]], i64 0, i32 0, i32 2
; CHECK-NEXT: store i32 20, i32* [[TMP48]], align 8
; CHECK-NEXT: br label [[BB52:%.*]]
; CHECK: bb52:
; CHECK-NEXT: br i1 [[C]], label [[BB68:%.*]], label [[BB59:%.*]]
; CHECK: bb59:
; CHECK-NEXT: call void @use.2(%struct.blam.4* [[TMP]])
; CHECK-NEXT: ret void
; CHECK: bb68:
; CHECK-NEXT: ret void
;
bb:
%tmp = alloca %struct.blam.4, align 8
%tmp36 = getelementptr inbounds %struct.blam.4, %struct.blam.4* %tmp, i64 0, i32 0, i32 1
%tmp37 = bitcast i64** %tmp36 to i8*
%tmp38 = getelementptr inbounds %struct.blam.4, %struct.blam.4* %tmp, i64 0, i32 0, i32 3
%tmp39 = bitcast i64* %tmp38 to i64*
store i64 0, i64* %tmp39, align 4
br i1 %c, label %bb46, label %bb47
bb46: ; preds = %bb12
call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(20) %tmp37, i8 0, i64 26, i1 false)
ret void
bb47: ; preds = %bb12
%tmp48 = getelementptr inbounds %struct.blam.4, %struct.blam.4* %tmp, i64 0, i32 0, i32 2
store i32 20, i32* %tmp48, align 8
br label %bb52
bb52: ; preds = %bb47
br i1 %c, label %bb68, label %bb59
bb59: ; preds = %bb52
call void @use.2(%struct.blam.4* %tmp)
ret void
bb68: ; preds = %bb52
ret void
}
declare void @use.2(%struct.blam.4*)
declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)