maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/early-ifcvt.ll

176 lines
5.5 KiB
LLVM
Raw Normal View History

The early if conversion pass is ready to be used as an opt-in. Enable the pass by default for targets that request it, and change the -enable-early-ifcvt to the opposite -disable-early-ifcvt. There are still some x86 regressions when enabling early if-conversion because of the missing machine models. Disable the pass for x86 until machine models are added. llvm-svn: 165075
2012-10-03 08:51:32 +08:00
; RUN: llc < %s -x86-early-ifcvt -stress-early-ifcvt | FileCheck %s
Add early if-conversion support to X86. Implement the TII hooks needed by EarlyIfConversion to create cmov instructions and estimate their latency. Early if-conversion is still not enabled by default. llvm-svn: 159695
2012-07-04 08:09:58 +08:00
target triple = "x86_64-apple-macosx10.8.0"
; CHECK: mm2
define i32 @mm2(i32* nocapture %p, i32 %n) nounwind uwtable readonly ssp {
entry:
br label %do.body
; CHECK: do.body
; Loop body has no branches before the backedge.
; CHECK-NOT: LBB
do.body:
%max.0 = phi i32 [ 0, %entry ], [ %max.1, %do.cond ]
%min.0 = phi i32 [ 0, %entry ], [ %min.1, %do.cond ]
%n.addr.0 = phi i32 [ %n, %entry ], [ %dec, %do.cond ]
%p.addr.0 = phi i32* [ %p, %entry ], [ %incdec.ptr, %do.cond ]
[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
%incdec.ptr = getelementptr inbounds i32, i32* %p.addr.0, i64 1
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%0 = load i32, i32* %p.addr.0, align 4
Add early if-conversion support to X86. Implement the TII hooks needed by EarlyIfConversion to create cmov instructions and estimate their latency. Early if-conversion is still not enabled by default. llvm-svn: 159695
2012-07-04 08:09:58 +08:00
%cmp = icmp sgt i32 %0, %max.0
br i1 %cmp, label %do.cond, label %if.else
if.else:
%cmp1 = icmp slt i32 %0, %min.0
%.min.0 = select i1 %cmp1, i32 %0, i32 %min.0
br label %do.cond
do.cond:
%max.1 = phi i32 [ %0, %do.body ], [ %max.0, %if.else ]
%min.1 = phi i32 [ %min.0, %do.body ], [ %.min.0, %if.else ]
; CHECK: decl %esi
; CHECK: jne LBB
%dec = add i32 %n.addr.0, -1
%tobool = icmp eq i32 %dec, 0
br i1 %tobool, label %do.end, label %do.body
do.end:
%sub = sub nsw i32 %max.1, %min.1
ret i32 %sub
}
Handle extra Tail predecessors in if-conversion. It is still possible to if-convert if the tail block has extra predecessors, but the tail phis must be rewritten instead of being removed. llvm-svn: 161781
2012-08-14 04:49:04 +08:00
; CHECK: multipreds
; Deal with alternative tail predecessors
; CHECK-NOT: LBB
; CHECK: cmov
; CHECK-NOT: LBB
; CHECK: cmov
; CHECK-NOT: LBB
; CHECK: fprintf
define void @multipreds(i32 %sw) nounwind uwtable ssp {
entry:
switch i32 %sw, label %if.then29 [
i32 0, label %if.then37
i32 127, label %if.end41
]
if.then29:
br label %if.end41
if.then37:
br label %if.end41
if.end41:
%exit_status.0 = phi i32 [ 2, %if.then29 ], [ 0, %if.then37 ], [ 66, %entry ]
call void (...)* @fprintf(i32 %exit_status.0) nounwind
unreachable
}
declare void @fprintf(...) nounwind
Don't crash on extra evil irreducible control flow. When the CFG contains a loop with multiple entry blocks, the traces computed by MachineTraceMetrics don't always have the same nice properties. Loop back-edges are normally excluded from traces, but MachineLoopInfo doesn't recognize loops with multiple entry blocks, so those back-edges may be included. Avoid asserting when that happens by adding an isEarlierInSameTrace() function that accurately determines if a dominating block is part of the same trace AND is above the currrent block in the trace. llvm-svn: 165434
2012-10-09 06:06:44 +08:00
; CHECK: BZ2_decompress
; This test case contains irreducible control flow, so MachineLoopInfo doesn't
; recognize the cycle in the CFG. This would confuse MachineTraceMetrics.
define void @BZ2_decompress(i8* %s) nounwind ssp {
entry:
switch i32 undef, label %sw.default [
i32 39, label %if.end.sw.bb2050_crit_edge
i32 36, label %sw.bb1788
i32 37, label %if.end.sw.bb1855_crit_edge
i32 40, label %sw.bb2409
i32 38, label %sw.bb1983
i32 44, label %if.end.sw.bb3058_crit_edge
]
if.end.sw.bb3058_crit_edge: ; preds = %entry
br label %save_state_and_return
if.end.sw.bb1855_crit_edge: ; preds = %entry
br label %save_state_and_return
if.end.sw.bb2050_crit_edge: ; preds = %entry
br label %sw.bb2050
sw.bb1788: ; preds = %entry
br label %save_state_and_return
sw.bb1983: ; preds = %entry
br i1 undef, label %save_state_and_return, label %if.then1990
if.then1990: ; preds = %sw.bb1983
br label %while.body2038
while.body2038: ; preds = %sw.bb2050, %if.then1990
%groupPos.8 = phi i32 [ 0, %if.then1990 ], [ %groupPos.9, %sw.bb2050 ]
br i1 undef, label %save_state_and_return, label %if.end2042
if.end2042: ; preds = %while.body2038
br i1 undef, label %if.end2048, label %while.end2104
if.end2048: ; preds = %if.end2042
[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
%bsLive2054.pre = getelementptr inbounds i8, i8* %s, i32 8
Don't crash on extra evil irreducible control flow. When the CFG contains a loop with multiple entry blocks, the traces computed by MachineTraceMetrics don't always have the same nice properties. Loop back-edges are normally excluded from traces, but MachineLoopInfo doesn't recognize loops with multiple entry blocks, so those back-edges may be included. Avoid asserting when that happens by adding an isEarlierInSameTrace() function that accurately determines if a dominating block is part of the same trace AND is above the currrent block in the trace. llvm-svn: 165434
2012-10-09 06:06:44 +08:00
br label %sw.bb2050
sw.bb2050: ; preds = %if.end2048, %if.end.sw.bb2050_crit_edge
%groupPos.9 = phi i32 [ 0, %if.end.sw.bb2050_crit_edge ], [ %groupPos.8, %if.end2048 ]
%and2064 = and i32 undef, 1
br label %while.body2038
while.end2104: ; preds = %if.end2042
br i1 undef, label %save_state_and_return, label %if.end2117
if.end2117: ; preds = %while.end2104
br i1 undef, label %while.body2161.lr.ph, label %while.body2145.lr.ph
while.body2145.lr.ph: ; preds = %if.end2117
br label %save_state_and_return
while.body2161.lr.ph: ; preds = %if.end2117
br label %save_state_and_return
sw.bb2409: ; preds = %entry
br label %save_state_and_return
sw.default: ; preds = %entry
call void @BZ2_bz__AssertH__fail() nounwind
br label %save_state_and_return
save_state_and_return:
%groupPos.14 = phi i32 [ 0, %sw.default ], [ %groupPos.8, %while.body2038 ], [ %groupPos.8, %while.end2104 ], [ 0, %if.end.sw.bb3058_crit_edge ], [ 0, %if.end.sw.bb1855_crit_edge ], [ %groupPos.8, %while.body2161.lr.ph ], [ %groupPos.8, %while.body2145.lr.ph ], [ 0, %sw.bb2409 ], [ 0, %sw.bb1788 ], [ 0, %sw.bb1983 ]
store i32 %groupPos.14, i32* undef, align 4
ret void
}
declare void @BZ2_bz__AssertH__fail()
Recommit r171461 which was incorrectly reverted. Mark DIV/IDIV instructions hasSideEffects=1 because they can trap when dividing by 0. This is needed to keep early if conversion from moving them across basic blocks. llvm-svn: 171608
2013-01-05 15:39:25 +08:00
; Make sure we don't speculate on div/idiv instructions
; CHECK: test_idiv
; CHECK-NOT: cmov
define i32 @test_idiv(i32 %a, i32 %b) nounwind uwtable readnone ssp {
%1 = icmp eq i32 %b, 0
br i1 %1, label %4, label %2
; <label>:2 ; preds = %0
%3 = sdiv i32 %a, %b
br label %4
; <label>:4 ; preds = %0, %2
%5 = phi i32 [ %3, %2 ], [ %a, %0 ]
ret i32 %5
}
; CHECK: test_div
; CHECK-NOT: cmov
define i32 @test_div(i32 %a, i32 %b) nounwind uwtable readnone ssp {
%1 = icmp eq i32 %b, 0
br i1 %1, label %4, label %2
; <label>:2 ; preds = %0
%3 = udiv i32 %a, %b
br label %4
; <label>:4 ; preds = %0, %2
%5 = phi i32 [ %3, %2 ], [ %a, %0 ]
ret i32 %5
}