llvm-6502/test/CodeGen/Mips/brdelayslot.ll

186 lines
4.5 KiB
LLVM
Raw Normal View History

; RUN: llc -march=mipsel -O0 < %s | FileCheck %s -check-prefix=None
; RUN: llc -march=mipsel < %s | FileCheck %s -check-prefix=Default
; RUN: llc -march=mipsel -O1 -relocation-model=static < %s | \
; RUN: FileCheck %s -check-prefix=STATICO1
; RUN: llc -march=mipsel -disable-mips-df-forward-search=false \
; RUN: -relocation-model=static < %s | FileCheck %s -check-prefix=FORWARD
; RUN: llc -march=mipsel -disable-mips-df-backward-search \
; RUN: -disable-mips-df-succbb-search=false < %s | \
; RUN: FileCheck %s -check-prefix=SUCCBB
define void @foo1() nounwind {
entry:
; Default: jalr
; Default-NOT: nop
; Default: jr
; Default-NOT: nop
; Default: .end
; None: jalr
; None: nop
; None: jr
; None: nop
; None: .end
tail call void @foo2(i32 3) nounwind
ret void
}
declare void @foo2(i32)
; Check that cvt.d.w goes into jalr's delay slot.
;
define void @foo3(i32 %a) nounwind {
entry:
; Default-LABEL: foo3:
; Default: jalr
; Default: cvt.d.w
%conv = sitofp i32 %a to double
tail call void @foo4(double %conv) nounwind
ret void
}
declare void @foo4(double)
@g2 = external global i32
@g1 = external global i32
@g3 = external global i32
; Check that branch delay slot can be filled with an instruction with operand
; $1.
;
; Default-LABEL: foo5:
; Default-NOT: nop
define void @foo5(i32 %a) nounwind {
entry:
%0 = load i32, i32* @g2, align 4
%tobool = icmp eq i32 %a, 0
br i1 %tobool, label %if.else, label %if.then
if.then:
%1 = load i32, i32* @g1, align 4
%add = add nsw i32 %1, %0
store i32 %add, i32* @g1, align 4
br label %if.end
if.else:
%2 = load i32, i32* @g3, align 4
%sub = sub nsw i32 %2, %0
store i32 %sub, i32* @g3, align 4
br label %if.end
if.end:
ret void
}
; Check that delay slot filler can place mov.s or mov.d in delay slot.
;
; Default-LABEL: foo6:
; Default-NOT: nop
; Default: .end foo6
define void @foo6(float %a0, double %a1) nounwind {
entry:
tail call void @foo7(double %a1, float %a0) nounwind
ret void
}
declare void @foo7(double, float)
; Check that a store can move past other memory instructions.
;
; STATICO1-LABEL: foo8:
; STATICO1: jalr ${{[0-9]+}}
; STATICO1-NEXT: sw ${{[0-9]+}}, %lo(g1)
@foo9 = common global void ()* null, align 4
define i32 @foo8(i32 %a) nounwind {
entry:
store i32 %a, i32* @g1, align 4
%0 = load void ()*, void ()** @foo9, align 4
tail call void %0() nounwind
%1 = load i32, i32* @g1, align 4
%add = add nsw i32 %1, %a
ret i32 %add
}
; Test searchForward. Check that the second jal's slot is filled with another
; instruction in the same block.
;
; FORWARD-LABEL: foo10:
; FORWARD: jal foo11
; FORWARD: jal foo11
; FORWARD-NOT: nop
; FORWARD: end foo10
define void @foo10() nounwind {
entry:
tail call void @foo11() nounwind
tail call void @foo11() nounwind
store i32 0, i32* @g1, align 4
tail call void @foo11() nounwind
store i32 0, i32* @g1, align 4
ret void
}
declare void @foo11()
; Check that delay slots of branches in both the entry block and loop body are
; filled.
;
; SUCCBB-LABEL: succbbs_loop1:
; SUCCBB: blez $5, $BB
; SUCCBB-NEXT: addiu
; SUCCBB: bnez ${{[0-9]+}}, $BB
; SUCCBB-NEXT: addiu
define i32 @succbbs_loop1(i32* nocapture %a, i32 %n) {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%s.06 = phi i32 [ %add, %for.body ], [ 0, %entry ]
%i.05 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230786 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 19:29:02 +00:00
%arrayidx = getelementptr inbounds i32, i32* %a, i32 %i.05
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %0, %s.06
%inc = add nsw i32 %i.05, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%s.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
ret i32 %s.0.lcssa
}
; Check that the first branch has its slot filled.
;
; SUCCBB-LABEL: succbbs_br1:
; SUCCBB: beqz ${{[0-9]+}}, $BB
; SUCCBB-NEXT: lw ${{[0-9]+}}, %got(foo101)(${{[0-9]+}})
define internal fastcc void @foo101() {
entry:
tail call void @foo100()
tail call void @foo100()
ret void
}
define void @succbbs_br1(i32 %a) {
entry:
%tobool = icmp eq i32 %a, 0
br i1 %tobool, label %if.end, label %if.then
if.then: ; preds = %entry
tail call fastcc void @foo101()
br label %if.end
if.end: ; preds = %entry, %if.then
ret void
}
declare void @foo100()