llvm-project/llvm/test/CodeGen/SystemZ/fp-sqrt-02.ll

170 lines
5.8 KiB
LLVM
Raw Normal View History

; Test 64-bit square root.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 \
; RUN: | FileCheck -check-prefix=CHECK -check-prefix=CHECK-SCALAR %s
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
declare double @llvm.sqrt.f64(double %f)
declare double @sqrt(double)
; Check register square root.
define double @f1(double %val) {
; CHECK-LABEL: f1:
; CHECK: sqdbr %f0, %f0
; CHECK: br %r14
%res = call double @llvm.sqrt.f64(double %val)
ret double %res
}
; Check the low end of the SQDB range.
define double @f2(double *%ptr) {
; CHECK-LABEL: f2:
; CHECK: sqdb %f0, 0(%r2)
; CHECK: br %r14
%val = load double , double *%ptr
%res = call double @llvm.sqrt.f64(double %val)
ret double %res
}
; Check the high end of the aligned SQDB range.
define double @f3(double *%base) {
; CHECK-LABEL: f3:
; CHECK: sqdb %f0, 4088(%r2)
; CHECK: br %r14
[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
%ptr = getelementptr double, double *%base, i64 511
%val = load double , double *%ptr
%res = call double @llvm.sqrt.f64(double %val)
ret double %res
}
; Check the next doubleword up, which needs separate address logic.
; Other sequences besides this one would be OK.
define double @f4(double *%base) {
; CHECK-LABEL: f4:
; CHECK: aghi %r2, 4096
; CHECK: sqdb %f0, 0(%r2)
; CHECK: br %r14
[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
%ptr = getelementptr double, double *%base, i64 512
%val = load double , double *%ptr
%res = call double @llvm.sqrt.f64(double %val)
ret double %res
}
; Check negative displacements, which also need separate address logic.
define double @f5(double *%base) {
; CHECK-LABEL: f5:
; CHECK: aghi %r2, -8
; CHECK: sqdb %f0, 0(%r2)
; CHECK: br %r14
[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
%ptr = getelementptr double, double *%base, i64 -1
%val = load double , double *%ptr
%res = call double @llvm.sqrt.f64(double %val)
ret double %res
}
; Check that SQDB allows indices.
define double @f6(double *%base, i64 %index) {
; CHECK-LABEL: f6:
; CHECK: sllg %r1, %r3, 3
; CHECK: sqdb %f0, 800(%r1,%r2)
; CHECK: br %r14
[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
%ptr1 = getelementptr double, double *%base, i64 %index
%ptr2 = getelementptr double, double *%ptr1, i64 100
%val = load double , double *%ptr2
%res = call double @llvm.sqrt.f64(double %val)
ret double %res
}
; Test a case where we spill the source of at least one SQDBR. We want
; to use SQDB if possible.
define void @f7(double *%ptr) {
; CHECK-LABEL: f7:
; CHECK-SCALAR: sqdb {{%f[0-9]+}}, 160(%r15)
; CHECK: br %r14
%val0 = load volatile double , double *%ptr
%val1 = load volatile double , double *%ptr
%val2 = load volatile double , double *%ptr
%val3 = load volatile double , double *%ptr
%val4 = load volatile double , double *%ptr
%val5 = load volatile double , double *%ptr
%val6 = load volatile double , double *%ptr
%val7 = load volatile double , double *%ptr
%val8 = load volatile double , double *%ptr
%val9 = load volatile double , double *%ptr
%val10 = load volatile double , double *%ptr
%val11 = load volatile double , double *%ptr
%val12 = load volatile double , double *%ptr
%val13 = load volatile double , double *%ptr
%val14 = load volatile double , double *%ptr
%val15 = load volatile double , double *%ptr
%val16 = load volatile double , double *%ptr
%sqrt0 = call double @llvm.sqrt.f64(double %val0)
%sqrt1 = call double @llvm.sqrt.f64(double %val1)
%sqrt2 = call double @llvm.sqrt.f64(double %val2)
%sqrt3 = call double @llvm.sqrt.f64(double %val3)
%sqrt4 = call double @llvm.sqrt.f64(double %val4)
%sqrt5 = call double @llvm.sqrt.f64(double %val5)
%sqrt6 = call double @llvm.sqrt.f64(double %val6)
%sqrt7 = call double @llvm.sqrt.f64(double %val7)
%sqrt8 = call double @llvm.sqrt.f64(double %val8)
%sqrt9 = call double @llvm.sqrt.f64(double %val9)
%sqrt10 = call double @llvm.sqrt.f64(double %val10)
%sqrt11 = call double @llvm.sqrt.f64(double %val11)
%sqrt12 = call double @llvm.sqrt.f64(double %val12)
%sqrt13 = call double @llvm.sqrt.f64(double %val13)
%sqrt14 = call double @llvm.sqrt.f64(double %val14)
%sqrt15 = call double @llvm.sqrt.f64(double %val15)
%sqrt16 = call double @llvm.sqrt.f64(double %val16)
store volatile double %val0, double *%ptr
store volatile double %val1, double *%ptr
store volatile double %val2, double *%ptr
store volatile double %val3, double *%ptr
store volatile double %val4, double *%ptr
store volatile double %val5, double *%ptr
store volatile double %val6, double *%ptr
store volatile double %val7, double *%ptr
store volatile double %val8, double *%ptr
store volatile double %val9, double *%ptr
store volatile double %val10, double *%ptr
store volatile double %val11, double *%ptr
store volatile double %val12, double *%ptr
store volatile double %val13, double *%ptr
store volatile double %val14, double *%ptr
store volatile double %val15, double *%ptr
store volatile double %val16, double *%ptr
store volatile double %sqrt0, double *%ptr
store volatile double %sqrt1, double *%ptr
store volatile double %sqrt2, double *%ptr
store volatile double %sqrt3, double *%ptr
store volatile double %sqrt4, double *%ptr
store volatile double %sqrt5, double *%ptr
store volatile double %sqrt6, double *%ptr
store volatile double %sqrt7, double *%ptr
store volatile double %sqrt8, double *%ptr
store volatile double %sqrt9, double *%ptr
store volatile double %sqrt10, double *%ptr
store volatile double %sqrt11, double *%ptr
store volatile double %sqrt12, double *%ptr
store volatile double %sqrt13, double *%ptr
store volatile double %sqrt14, double *%ptr
store volatile double %sqrt15, double *%ptr
store volatile double %sqrt16, double *%ptr
ret void
}
; Check that a call to the normal sqrt function is lowered.
define double @f8(double %dummy, double %val) {
; CHECK-LABEL: f8:
; CHECK: sqdbr %f0, %f2
; CHECK: cdbr %f0, %f0
; CHECK: bnor %r14
; CHECK: ldr %f0, %f2
; CHECK: jg sqrt@PLT
%res = tail call double @sqrt(double %val)
ret double %res
}