llvm-6502/test/CodeGen/PowerPC/2007-11-16-landingpad-split.ll

68 lines
2.3 KiB
LLVM
Raw Normal View History

; RUN: llc -mcpu=g5 < %s | FileCheck %s
Add the ability to use GEPs for address sinking in CGP The current memory-instruction optimization logic in CGP, which sinks parts of the address computation that can be adsorbed by the addressing mode, does this by explicitly converting the relevant part of the address computation into IR-level integer operations (making use of ptrtoint and inttoptr). For most targets this is currently not a problem, but for targets wishing to make use of IR-level aliasing analysis during CodeGen, the use of ptrtoint/inttoptr is a problem for two reasons: 1. BasicAA becomes less powerful in the face of the ptrtoint/inttoptr 2. In cases where type-punning was used, and BasicAA was used to override TBAA, BasicAA may no longer do so. (this had forced us to disable all use of TBAA in CodeGen; something which we can now enable again) This (use of GEPs instead of ptrtoint/inttoptr) is not currently enabled by default (except for those targets that use AA during CodeGen), and so aside from some PowerPC subtargets and SystemZ, there should be no change in behavior. We may be able to switch completely away from the ptrtoint/inttoptr sinking on all targets, but further testing is required. I've doubled-up on a number of existing tests that are sensitive to the address sinking behavior (including some store-merging tests that are sensitive to the order of the resulting ADD operations at the SDAG level). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206092 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-12 00:59:48 +00:00
; RUN: llc -mcpu=g5 -addr-sink-using-gep=1 < %s | FileCheck %s
;; Formerly crashed, see PR 1508
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f128:64:128"
target triple = "powerpc64-apple-darwin8"
%struct.Range = type { i64, i64 }
; CHECK: .cfi_startproc
; CHECK: .cfi_personality 155, L___gxx_personality_v0$non_lazy_ptr
; CHECK: .cfi_lsda 16, Lexception0
; CHECK: .cfi_def_cfa_offset 176
; CHECK: .cfi_offset r31, -8
; CHECK: .cfi_offset lr, 16
; CHECK: .cfi_def_cfa_register r31
; CHECK: .cfi_offset r27, -16
; CHECK: .cfi_offset r28, -24
; CHECK: .cfi_offset r29, -32
; CHECK: .cfi_offset r30, -40
; CHECK: .cfi_endproc
define void @Bork(i64 %range.0.0, i64 %range.0.1, i64 %size) {
entry:
%effectiveRange = alloca %struct.Range, align 8 ; <%struct.Range*> [#uses=2]
%tmp4 = call i8* @llvm.stacksave() ; <i8*> [#uses=1]
%size1 = trunc i64 %size to i32 ; <i32> [#uses=1]
%tmp17 = alloca i8*, i32 %size1 ; <i8**> [#uses=1]
invoke void @Foo(i8** %tmp17)
to label %bb30.preheader unwind label %unwind
bb30.preheader: ; preds = %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
%tmp26 = getelementptr %struct.Range, %struct.Range* %effectiveRange, i64 0, i32 1 ; <i64*> [#uses=1]
br label %bb30
unwind: ; preds = %cond_true, %entry
%exn = landingpad {i8*, i32} personality i32 (...)* @__gxx_personality_v0
catch i8* null
call void @llvm.stackrestore(i8* %tmp4)
resume { i8*, i32 } %exn
invcont23: ; preds = %cond_true
%tmp27 = load i64, i64* %tmp26, align 8 ; <i64> [#uses=1]
%tmp28 = sub i64 %range_addr.1.0, %tmp27 ; <i64> [#uses=1]
br label %bb30
bb30: ; preds = %invcont23, %bb30.preheader
%range_addr.1.0 = phi i64 [ %tmp28, %invcont23 ], [ %range.0.1, %bb30.preheader ] ; <i64> [#uses=2]
%tmp33 = icmp eq i64 %range_addr.1.0, 0 ; <i1> [#uses=1]
br i1 %tmp33, label %cleanup, label %cond_true
cond_true: ; preds = %bb30
invoke void @Bar(i64 %range.0.0, %struct.Range* %effectiveRange)
to label %invcont23 unwind label %unwind
cleanup: ; preds = %bb30
ret void
}
declare i8* @llvm.stacksave() nounwind
declare void @Foo(i8**)
declare void @Bar(i64, %struct.Range*)
declare void @llvm.stackrestore(i8*) nounwind
declare i32 @__gxx_personality_v0(...)