6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-18 10:31:57 +00:00
Code Issues Projects Releases Wiki Activity
6aebd393f0
llvm-6502/test/CodeGen/AArch64/arm64-ccmp.ll

290 lines
7.0 KiB
LLVM
Raw Normal View History

AArch64/ARM64: move ARM64 into AArch64's place This commit starts with a "git mv ARM64 AArch64" and continues out from there, renaming the C++ classes, intrinsics, and other target-local objects for consistency. "ARM64" test directories are also moved, and tests that began their life in ARM64 use an arm64 triple, those from AArch64 use an aarch64 triple. Both should be equivalent though. This finishes the AArch64 merge, and everyone should feel free to continue committing as normal now. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209577 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-24 12:50:23 +00:00
; RUN: llc < %s -mcpu=cyclone -verify-machineinstrs -aarch64-ccmp -aarch64-stress-ccmp | 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
target triple = "arm64-apple-ios"
; CHECK: single_same
; CHECK: cmp w0, #5
; CHECK-NEXT: ccmp w1, #17, #4, ne
; CHECK-NEXT: b.ne
; CHECK: %if.then
; CHECK: bl _foo
; CHECK: %if.end
define i32 @single_same(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 5
%cmp1 = icmp eq i32 %b, 17
%or.cond = or i1 %cmp, %cmp1
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Different condition codes for the two compares.
; CHECK: single_different
; CHECK: cmp w0, #6
; CHECK-NEXT: ccmp w1, #17, #0, ge
; CHECK-NEXT: b.eq
; CHECK: %if.then
; CHECK: bl _foo
; CHECK: %if.end
define i32 @single_different(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp sle i32 %a, 5
%cmp1 = icmp ne i32 %b, 17
%or.cond = or i1 %cmp, %cmp1
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Second block clobbers the flags, can't convert (easily).
; CHECK: single_flagclobber
; CHECK: cmp
; CHECK: b.eq
; CHECK: cmp
; CHECK: b.gt
define i32 @single_flagclobber(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 5
br i1 %cmp, label %if.then, label %lor.lhs.false
lor.lhs.false: ; preds = %entry
%cmp1 = icmp slt i32 %b, 7
%mul = shl nsw i32 %b, 1
%add = add nsw i32 %b, 1
%cond = select i1 %cmp1, i32 %mul, i32 %add
%cmp2 = icmp slt i32 %cond, 17
br i1 %cmp2, label %if.then, label %if.end
if.then: ; preds = %lor.lhs.false, %entry
%call = tail call i32 @foo() nounwind
br label %if.end
if.end: ; preds = %if.then, %lor.lhs.false
ret i32 7
}
; Second block clobbers the flags and ends with a tbz terminator.
; CHECK: single_flagclobber_tbz
; CHECK: cmp
; CHECK: b.eq
; CHECK: cmp
; CHECK: tbz
define i32 @single_flagclobber_tbz(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 5
br i1 %cmp, label %if.then, label %lor.lhs.false
lor.lhs.false: ; preds = %entry
%cmp1 = icmp slt i32 %b, 7
%mul = shl nsw i32 %b, 1
%add = add nsw i32 %b, 1
%cond = select i1 %cmp1, i32 %mul, i32 %add
%and = and i32 %cond, 8
%cmp2 = icmp ne i32 %and, 0
br i1 %cmp2, label %if.then, label %if.end
if.then: ; preds = %lor.lhs.false, %entry
%call = tail call i32 @foo() nounwind
br label %if.end
if.end: ; preds = %if.then, %lor.lhs.false
ret i32 7
}
; Speculatively execute division by zero.
; The sdiv/udiv instructions do not trap when the divisor is zero, so they are
; safe to speculate.
; CHECK: speculate_division
; CHECK-NOT: cmp
; CHECK: sdiv
; CHECK: cmp
; CHECK-NEXT: ccmp
define i32 @speculate_division(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp sgt i32 %a, 0
br i1 %cmp, label %land.lhs.true, label %if.end
land.lhs.true:
%div = sdiv i32 %b, %a
%cmp1 = icmp slt i32 %div, 17
br i1 %cmp1, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Floating point compare.
; CHECK: single_fcmp
; CHECK: cmp
; CHECK-NOT: b.
; CHECK: fccmp {{.*}}, #8, ge
; CHECK: b.lt
define i32 @single_fcmp(i32 %a, float %b) nounwind ssp {
entry:
%cmp = icmp sgt i32 %a, 0
br i1 %cmp, label %land.lhs.true, label %if.end
land.lhs.true:
%conv = sitofp i32 %a to float
%div = fdiv float %b, %conv
%cmp1 = fcmp oge float %div, 1.700000e+01
br i1 %cmp1, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Chain multiple compares.
; CHECK: multi_different
; CHECK: cmp
; CHECK: ccmp
; CHECK: ccmp
; CHECK: b.
define void @multi_different(i32 %a, i32 %b, i32 %c) nounwind ssp {
entry:
%cmp = icmp sgt i32 %a, %b
br i1 %cmp, label %land.lhs.true, label %if.end
land.lhs.true:
%div = sdiv i32 %b, %a
%cmp1 = icmp eq i32 %div, 5
%cmp4 = icmp sgt i32 %div, %c
%or.cond = and i1 %cmp1, %cmp4
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret void
}
; Convert a cbz in the head block.
; CHECK: cbz_head
; CHECK: cmp w0, #0
; CHECK: ccmp
define i32 @cbz_head(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 0
%cmp1 = icmp ne i32 %b, 17
%or.cond = or i1 %cmp, %cmp1
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Check that the immediate operand is in range. The ccmp instruction encodes a
; smaller range of immediates than subs/adds.
; The ccmp immediates must be in the range 0-31.
; CHECK: immediate_range
; CHECK-NOT: ccmp
define i32 @immediate_range(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 5
%cmp1 = icmp eq i32 %b, 32
%or.cond = or i1 %cmp, %cmp1
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Convert a cbz in the second block.
; CHECK: cbz_second
; CHECK: cmp w0, #0
; CHECK: ccmp w1, #0, #0, ne
; CHECK: b.eq
define i32 @cbz_second(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 0
%cmp1 = icmp ne i32 %b, 0
%or.cond = or i1 %cmp, %cmp1
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
; Convert a cbnz in the second block.
; CHECK: cbnz_second
; CHECK: cmp w0, #0
; CHECK: ccmp w1, #0, #4, ne
; CHECK: b.ne
define i32 @cbnz_second(i32 %a, i32 %b) nounwind ssp {
entry:
%cmp = icmp eq i32 %a, 0
%cmp1 = icmp eq i32 %b, 0
%or.cond = or i1 %cmp, %cmp1
br i1 %or.cond, label %if.then, label %if.end
if.then:
%call = tail call i32 @foo() nounwind
br label %if.end
if.end:
ret i32 7
}
declare i32 @foo()
%str1 = type { %str2 }
%str2 = type { [24 x i8], i8*, i32, %str1*, i32, [4 x i8], %str1*, %str1*, %str1*, %str1*, %str1*, %str1*, %str1*, %str1*, %str1*, i8*, i8, i8*, %str1*, i8* }
; Test case distilled from 126.gcc.
; The phi in sw.bb.i.i gets multiple operands for the %entry predecessor.
; CHECK: build_modify_expr
define void @build_modify_expr() nounwind ssp {
entry:
switch i32 undef, label %sw.bb.i.i [
i32 69, label %if.end85
i32 70, label %if.end85
i32 71, label %if.end85
i32 72, label %if.end85
i32 73, label %if.end85
i32 105, label %if.end85
i32 106, label %if.end85
]
if.end85:
ret void
sw.bb.i.i:
%ref.tr.i.i = phi %str1* [ %0, %sw.bb.i.i ], [ undef, %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
%operands.i.i = getelementptr inbounds %str1, %str1* %ref.tr.i.i, i64 0, i32 0, i32 2
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
%arrayidx.i.i = bitcast i32* %operands.i.i to %str1**
[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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 21:17:42 +00:00
%0 = load %str1*, %str1** %arrayidx.i.i, align 8
[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
%code1.i.i.phi.trans.insert = getelementptr inbounds %str1, %str1* %0, i64 0, i32 0, i32 0, i64 16
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
br label %sw.bb.i.i
}
Reference in New Issue Copy Permalink