RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-21 11:38:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
a21d820952
llvm/test/CodeGen/AArch64/arm64-addr-mode-folding.ll

172 lines
5.8 KiB
LLVM
Raw Normal View History

[AArch64] Enable SeparateConstOffsetFromGEP, EarlyCSE and LICM passes on AArch64 backend. SeparateConstOffsetFromGEP can gives more optimizaiton opportunities related to GEPs, which benefits EarlyCSE and LICM. By enabling these passes we can have better address calculations and generate a better addressing mode. Some SPEC 2006 benchmarks (astar, gobmk, namd) have obvious improvements on Cortex-A57. Reviewed in http://reviews.llvm.org/D5864. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222331 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-19 06:39:53 +00:00
; RUN: llc -O3 -mtriple arm64-apple-ios3 -aarch64-gep-opt=false %s -o - | FileCheck %s
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205090 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-29 10:18:08 +00:00
; <rdar://problem/13621857>
@block = common global i8* null, align 8
define i32 @fct(i32 %i1, i32 %i2) {
; CHECK: @fct
; Sign extension is used more than once, thus it should not be folded.
Fix some doc and comment typos git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205899 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-09 14:47:27 +00:00
; CodeGenPrepare is not sharing sext across uses, thus this is folded because
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205090 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-29 10:18:08 +00:00
; of that.
; _CHECK-NOT_: , sxtw]
entry:
%idxprom = sext i32 %i1 to i64
%0 = load i8** @block, align 8
%arrayidx = getelementptr inbounds i8* %0, i64 %idxprom
%1 = load i8* %arrayidx, align 1
%idxprom1 = sext i32 %i2 to i64
%arrayidx2 = getelementptr inbounds i8* %0, i64 %idxprom1
%2 = load i8* %arrayidx2, align 1
%cmp = icmp eq i8 %1, %2
br i1 %cmp, label %if.end, label %if.then
if.then: ; preds = %entry
%cmp7 = icmp ugt i8 %1, %2
%conv8 = zext i1 %cmp7 to i32
br label %return
if.end: ; preds = %entry
%inc = add nsw i32 %i1, 1
%inc9 = add nsw i32 %i2, 1
%idxprom10 = sext i32 %inc to i64
%arrayidx11 = getelementptr inbounds i8* %0, i64 %idxprom10
%3 = load i8* %arrayidx11, align 1
%idxprom12 = sext i32 %inc9 to i64
%arrayidx13 = getelementptr inbounds i8* %0, i64 %idxprom12
%4 = load i8* %arrayidx13, align 1
%cmp16 = icmp eq i8 %3, %4
br i1 %cmp16, label %if.end23, label %if.then18
if.then18: ; preds = %if.end
%cmp21 = icmp ugt i8 %3, %4
%conv22 = zext i1 %cmp21 to i32
br label %return
if.end23: ; preds = %if.end
%inc24 = add nsw i32 %i1, 2
%inc25 = add nsw i32 %i2, 2
%idxprom26 = sext i32 %inc24 to i64
%arrayidx27 = getelementptr inbounds i8* %0, i64 %idxprom26
%5 = load i8* %arrayidx27, align 1
%idxprom28 = sext i32 %inc25 to i64
%arrayidx29 = getelementptr inbounds i8* %0, i64 %idxprom28
%6 = load i8* %arrayidx29, align 1
%cmp32 = icmp eq i8 %5, %6
br i1 %cmp32, label %return, label %if.then34
if.then34: ; preds = %if.end23
%cmp37 = icmp ugt i8 %5, %6
%conv38 = zext i1 %cmp37 to i32
br label %return
return: ; preds = %if.end23, %if.then34, %if.then18, %if.then
%retval.0 = phi i32 [ %conv8, %if.then ], [ %conv22, %if.then18 ], [ %conv38, %if.then34 ], [ 1, %if.end23 ]
ret i32 %retval.0
}
define i32 @fct1(i32 %i1, i32 %i2) optsize {
; CHECK: @fct1
; Addressing are folded when optimizing for code size.
; CHECK: , sxtw]
; CHECK: , sxtw]
entry:
%idxprom = sext i32 %i1 to i64
%0 = load i8** @block, align 8
%arrayidx = getelementptr inbounds i8* %0, i64 %idxprom
%1 = load i8* %arrayidx, align 1
%idxprom1 = sext i32 %i2 to i64
%arrayidx2 = getelementptr inbounds i8* %0, i64 %idxprom1
%2 = load i8* %arrayidx2, align 1
%cmp = icmp eq i8 %1, %2
br i1 %cmp, label %if.end, label %if.then
if.then: ; preds = %entry
%cmp7 = icmp ugt i8 %1, %2
%conv8 = zext i1 %cmp7 to i32
br label %return
if.end: ; preds = %entry
%inc = add nsw i32 %i1, 1
%inc9 = add nsw i32 %i2, 1
%idxprom10 = sext i32 %inc to i64
%arrayidx11 = getelementptr inbounds i8* %0, i64 %idxprom10
%3 = load i8* %arrayidx11, align 1
%idxprom12 = sext i32 %inc9 to i64
%arrayidx13 = getelementptr inbounds i8* %0, i64 %idxprom12
%4 = load i8* %arrayidx13, align 1
%cmp16 = icmp eq i8 %3, %4
br i1 %cmp16, label %if.end23, label %if.then18
if.then18: ; preds = %if.end
%cmp21 = icmp ugt i8 %3, %4
%conv22 = zext i1 %cmp21 to i32
br label %return
if.end23: ; preds = %if.end
%inc24 = add nsw i32 %i1, 2
%inc25 = add nsw i32 %i2, 2
%idxprom26 = sext i32 %inc24 to i64
%arrayidx27 = getelementptr inbounds i8* %0, i64 %idxprom26
%5 = load i8* %arrayidx27, align 1
%idxprom28 = sext i32 %inc25 to i64
%arrayidx29 = getelementptr inbounds i8* %0, i64 %idxprom28
%6 = load i8* %arrayidx29, align 1
%cmp32 = icmp eq i8 %5, %6
br i1 %cmp32, label %return, label %if.then34
if.then34: ; preds = %if.end23
%cmp37 = icmp ugt i8 %5, %6
%conv38 = zext i1 %cmp37 to i32
br label %return
return: ; preds = %if.end23, %if.then34, %if.then18, %if.then
%retval.0 = phi i32 [ %conv8, %if.then ], [ %conv22, %if.then18 ], [ %conv38, %if.then34 ], [ 1, %if.end23 ]
ret i32 %retval.0
}
; CHECK: @test
; CHECK-NOT: , uxtw #2]
define i32 @test(i32* %array, i8 zeroext %c, i32 %arg) {
entry:
%conv = zext i8 %c to i32
%add = sub i32 0, %arg
%tobool = icmp eq i32 %conv, %add
br i1 %tobool, label %if.end, label %if.then
if.then: ; preds = %entry
%idxprom = zext i8 %c to i64
%arrayidx = getelementptr inbounds i32* %array, i64 %idxprom
%0 = load volatile i32* %arrayidx, align 4
%1 = load volatile i32* %arrayidx, align 4
%add3 = add nsw i32 %1, %0
br label %if.end
if.end: ; preds = %entry, %if.then
%res.0 = phi i32 [ %add3, %if.then ], [ 0, %entry ]
ret i32 %res.0
}
; CHECK: @test2
; CHECK: , uxtw #2]
; CHECK: , uxtw #2]
define i32 @test2(i32* %array, i8 zeroext %c, i32 %arg) optsize {
entry:
%conv = zext i8 %c to i32
%add = sub i32 0, %arg
%tobool = icmp eq i32 %conv, %add
br i1 %tobool, label %if.end, label %if.then
if.then: ; preds = %entry
%idxprom = zext i8 %c to i64
%arrayidx = getelementptr inbounds i32* %array, i64 %idxprom
%0 = load volatile i32* %arrayidx, align 4
%1 = load volatile i32* %arrayidx, align 4
%add3 = add nsw i32 %1, %0
br label %if.end
if.end: ; preds = %entry, %if.then
%res.0 = phi i32 [ %add3, %if.then ], [ 0, %entry ]
ret i32 %res.0
}
Reference in New Issue Copy Permalink