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/LICM/argmemonly-call.ll

135 lines
3.5 KiB
LLVM
Raw Normal View History

[LICM] Add a diagnostic analysis for identifying alias information Summary: Currently, in LICM, we use the alias set tracker to identify if the instruction (we're interested in hoisting) aliases with instruction that modifies that memory location. This patch adds an LICM alias analysis diagnostic tool that checks the mod ref info of the instruction we are interested in hoisting/sinking, with every instruction in the loop. Because of O(N^2) complexity this is now only a diagnostic tool to show the limitation we have with the alias set tracker and is OFF by default. Test cases show the difference with the diagnostic analysis tool, where we're able to hoist out loads and readonly + argmemonly calls from the loop, where the alias set tracker analysis is not able to hoist these instructions out. Reviewers: reames, mkazantsev, fedor.sergeev, hfinkel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D50854 llvm-svn: 340026
2018-08-17 21:44:00 +08:00
; RUN: opt -S -basicaa -licm -licm-n2-threshold=0 %s | FileCheck %s
; RUN: opt -licm -basicaa -licm-n2-threshold=200 < %s -S | FileCheck %s --check-prefix=ALIAS-N2
; RUN: opt -aa-pipeline=basic-aa -licm-n2-threshold=0 -passes='require<aa>,require<targetir>,require<scalar-evolution>,require<opt-remark-emit>,loop(licm)' < %s -S | FileCheck %s
; RUN: opt -aa-pipeline=basic-aa -licm-n2-threshold=200 -passes='require<aa>,require<targetir>,require<scalar-evolution>,require<opt-remark-emit>,loop(licm)' < %s -S | FileCheck %s --check-prefix=ALIAS-N2
[LICM] Hoist calls to readonly argmemonly functions even with stores in the loop We know that an argmemonly function can only access memory pointed to by it's pointer arguments. Rather than needing to consider all possible stores as aliasing (as we do for a readonly function), we can only consider the aliasing of the pointer arguments. Note that this change only addresses hoisting. I'm thinking about how to address speculation safety as well, but that will be a different change. FYI, argmemonly disallows accessing memory through non-pointer typed arguments. Differential Revision: http://reviews.llvm.org/D12771 llvm-svn: 248220
2015-09-22 06:27:59 +08:00
declare i32 @foo() readonly argmemonly nounwind
declare i32 @foo2() readonly nounwind
declare i32 @bar(i32* %loc2) readonly argmemonly nounwind
define void @test(i32* %loc) {
; CHECK-LABEL: @test
; CHECK: @foo
; CHECK-LABEL: loop:
br label %loop
loop:
%res = call i32 @foo()
store i32 %res, i32* %loc
br label %loop
}
; Negative test: show argmemonly is required
define void @test_neg(i32* %loc) {
; CHECK-LABEL: @test_neg
; CHECK-LABEL: loop:
; CHECK: @foo
br label %loop
loop:
%res = call i32 @foo2()
store i32 %res, i32* %loc
br label %loop
}
define void @test2(i32* noalias %loc, i32* noalias %loc2) {
; CHECK-LABEL: @test2
; CHECK: @bar
; CHECK-LABEL: loop:
br label %loop
loop:
%res = call i32 @bar(i32* %loc2)
store i32 %res, i32* %loc
br label %loop
}
; Negative test: %might clobber gep
define void @test3(i32* %loc) {
; CHECK-LABEL: @test3
; CHECK-LABEL: loop:
; CHECK: @bar
br label %loop
loop:
%res = call i32 @bar(i32* %loc)
%gep = getelementptr i32, i32 *%loc, i64 1000000
store i32 %res, i32* %gep
br label %loop
}
; Negative test: %loc might alias %loc2
define void @test4(i32* %loc, i32* %loc2) {
; CHECK-LABEL: @test4
; CHECK-LABEL: loop:
; CHECK: @bar
br label %loop
loop:
%res = call i32 @bar(i32* %loc2)
store i32 %res, i32* %loc
br label %loop
}
[LICM] Add a diagnostic analysis for identifying alias information Summary: Currently, in LICM, we use the alias set tracker to identify if the instruction (we're interested in hoisting) aliases with instruction that modifies that memory location. This patch adds an LICM alias analysis diagnostic tool that checks the mod ref info of the instruction we are interested in hoisting/sinking, with every instruction in the loop. Because of O(N^2) complexity this is now only a diagnostic tool to show the limitation we have with the alias set tracker and is OFF by default. Test cases show the difference with the diagnostic analysis tool, where we're able to hoist out loads and readonly + argmemonly calls from the loop, where the alias set tracker analysis is not able to hoist these instructions out. Reviewers: reames, mkazantsev, fedor.sergeev, hfinkel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D50854 llvm-svn: 340026
2018-08-17 21:44:00 +08:00
declare i32 @foo_new(i32*) readonly
; With the default AST mechanism used by LICM for alias analysis,
; we clump foo_new with bar.
; With the N2 Alias analysis diagnostic tool, we are able to hoist the
; argmemonly bar call out of the loop.
define void @test5(i32* %loc2, i32* noalias %loc) {
; ALIAS-N2-LABEL: @test5
; ALIAS-N2: @bar
; ALIAS-N2-LABEL: loop:
; CHECK-LABEL: @test5
; CHECK-LABEL: loop:
; CHECK: @bar
br label %loop
loop:
%res1 = call i32 @bar(i32* %loc2)
%res = call i32 @foo_new(i32* %loc2)
store volatile i32 %res1, i32* %loc
br label %loop
}
[LICM][NFC] Add tests from D50730 Landing tests so corresponding change can show effects clearly. see D50730 [AST] Generalize argument specific aliasing llvm-svn: 340243
2018-08-21 08:37:09 +08:00
; memcpy doesn't write to it's source argument, so loads to that location
; can still be hoisted
define void @test6(i32* noalias %loc, i32* noalias %loc2) {
; CHECK-LABEL: @test6
; CHECK: %val = load i32, i32* %loc2
; CHECK-LABEL: loop:
; CHECK: @llvm.memcpy
br label %loop
loop:
%val = load i32, i32* %loc2
store i32 %val, i32* %loc
%dest = bitcast i32* %loc to i8*
%src = bitcast i32* %loc2 to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dest, i8* %src, i64 8, i1 false)
br label %loop
}
define void @test7(i32* noalias %loc, i32* noalias %loc2) {
; CHECK-LABEL: @test7
; CHECK: %val = load i32, i32* %loc2
[AST] Generalize argument specific aliasing AliasSetTracker has special case handling for memset, memcpy and memmove which pre-existed argmemonly on functions and readonly and writeonly on arguments. This patch generalizes it using the AA infrastructure to any call correctly annotated. The motivation here is to cut down on confusion, not performance per se. For most instructions, there is a direct mapping to alias set. However, this is not guaranteed by the interface and was not in fact true for these three intrinsics *and only these three intrinsics*. I kept getting myself confused about this invariant, so I figured it would be good to clearly distinguish between a instructions and alias sets. Calls happened to be an easy target. The nice side effect is that custom implementations of memset/memcpy/memmove - including wrappers discovered by IPO - can now be optimized the same as builts by LICM. Note: The actual removal of the memset/memtransfer specific handling will happen in a follow on NFC patch. It was originally part of this one, but separate for ease of review and rebase. Differential Revision: https://reviews.llvm.org/D50730 llvm-svn: 341713
2018-09-08 05:36:11 +08:00
; CHECK-LABEL: loop:
[LICM][NFC] Add tests from D50730 Landing tests so corresponding change can show effects clearly. see D50730 [AST] Generalize argument specific aliasing llvm-svn: 340243
2018-08-21 08:37:09 +08:00
; CHECK: @custom_memcpy
br label %loop
loop:
%val = load i32, i32* %loc2
store i32 %val, i32* %loc
%dest = bitcast i32* %loc to i8*
%src = bitcast i32* %loc2 to i8*
call void @custom_memcpy(i8* %dest, i8* %src)
br label %loop
}
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)
declare void @custom_memcpy(i8* nocapture writeonly, i8* nocapture readonly) argmemonly nounwind