llvm-project/llvm/test/CodeGen/ARM/thumb1-varalloc.ll

126 lines
3.1 KiB
LLVM
Raw Normal View History

; RUN: llc < %s -mtriple=thumbv6-apple-darwin | FileCheck %s
; RUN: llc < %s -mtriple=thumbv6-apple-darwin -regalloc=basic | FileCheck %s
; RUN: llc < %s -o %t -filetype=obj -mtriple=thumbv6-apple-darwin
; RUN: llvm-objdump -triple=thumbv6-apple-darwin -d %t | FileCheck %s
@__bar = external hidden global i8*
@__baz = external hidden global i8*
; rdar://8819685
define i8* @_foo() {
entry:
; CHECK-LABEL: foo:
%size = alloca i32, align 4
%0 = load i8** @__bar, align 4
%1 = icmp eq i8* %0, null
br i1 %1, label %bb1, label %bb3
; CHECK: bne
bb1:
store i32 1026, i32* %size, align 4
%2 = alloca [1026 x i8], align 1
; CHECK: mov [[R0:r[0-9]+]], sp
; CHECK: adds {{r[0-9]+}}, [[R0]], {{r[0-9]+}}
[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 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%3 = getelementptr inbounds [1026 x i8], [1026 x i8]* %2, i32 0, i32 0
%4 = call i32 @_called_func(i8* %3, i32* %size) nounwind
%5 = icmp eq i32 %4, 0
br i1 %5, label %bb2, label %bb3
bb2:
%6 = call i8* @strdup(i8* %3) nounwind
store i8* %6, i8** @__baz, align 4
br label %bb3
bb3:
%.0 = phi i8* [ %0, %entry ], [ %6, %bb2 ], [ %3, %bb1 ]
; CHECK: subs r4, #5
; CHECK-NEXT: mov sp, r4
; CHECK-NEXT: pop {r4, r5, r6, r7, pc}
ret i8* %.0
}
declare noalias i8* @strdup(i8* nocapture) nounwind
declare i32 @_called_func(i8*, i32*) nounwind
; Simple variable ending up *at* sp.
define void @test_simple_var() {
; CHECK-LABEL: test_simple_var:
%addr32 = alloca i32
%addr8 = bitcast i32* %addr32 to i8*
; CHECK: mov r0, sp
; CHECK-NOT: adds r0
; CHECK: blx
call void @take_ptr(i8* %addr8)
ret void
}
; Simple variable ending up at aligned offset from sp.
define void @test_local_var_addr_aligned() {
; CHECK-LABEL: test_local_var_addr_aligned:
%addr1.32 = alloca i32
%addr1 = bitcast i32* %addr1.32 to i8*
%addr2.32 = alloca i32
%addr2 = bitcast i32* %addr2.32 to i8*
; CHECK: add r0, sp, #{{[0-9]+}}
; CHECK: blx
call void @take_ptr(i8* %addr1)
; CHECK: mov r0, sp
; CHECK-NOT: add r0
; CHECK: blx
call void @take_ptr(i8* %addr2)
ret void
}
; Simple variable ending up at aligned offset from sp.
define void @test_local_var_big_offset() {
; CHECK-LABEL: test_local_var_big_offset:
%addr1.32 = alloca i32, i32 257
%addr1 = bitcast i32* %addr1.32 to i8*
%addr2.32 = alloca i32, i32 257
; CHECK: add [[RTMP:r[0-9]+]], sp, #1020
; CHECK: adds [[RTMP]], #8
; CHECK: blx
call void @take_ptr(i8* %addr1)
ret void
}
; Max range addressable with tADDrSPi
define void @test_local_var_offset_1020() {
; CHECK-LABEL: test_local_var_offset_1020
%addr1 = alloca i8, i32 4
%addr2 = alloca i8, i32 1020
; CHECK: add r0, sp, #1020
; CHECK-NEXT: blx
call void @take_ptr(i8* %addr1)
ret void
}
; Max range addressable with tADDrSPi + tADDi8 is 1275, however the automatic
; 4-byte aligning of objects on the stack combined with 8-byte stack alignment
; means that 1268 is the max offset we can use.
define void @test_local_var_offset_1268() {
; CHECK-LABEL: test_local_var_offset_1268
%addr1 = alloca i8, i32 1
%addr2 = alloca i8, i32 1268
; CHECK: add r0, sp, #1020
; CHECK: adds r0, #248
; CHECK-NEXT: blx
call void @take_ptr(i8* %addr1)
ret void
}
declare void @take_ptr(i8*)