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/NVPTX/access-non-generic.ll

92 lines
3.5 KiB
LLVM
Raw Normal View History

Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix PTX
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix PTX
; RUN: opt < %s -S -nvptx-favor-non-generic -dce | FileCheck %s --check-prefix IR
@array = internal addrspace(3) global [10 x float] zeroinitializer, align 4
@scalar = internal addrspace(3) global float 0.000000e+00, align 4
; Verifies nvptx-favor-non-generic correctly optimizes generic address space
; usage to non-generic address space usage for the patterns we claim to handle:
; 1. load cast
; 2. store cast
; 3. load gep cast
; 4. store gep cast
; gep and cast can be an instruction or a constant expression. This function
; tries all possible combinations.
define float @ld_st_shared_f32(i32 %i, float %v) {
; IR-LABEL: @ld_st_shared_f32
; IR-NOT: addrspacecast
; PTX-LABEL: ld_st_shared_f32(
; load cast
[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
%1 = load float, float* addrspacecast (float addrspace(3)* @scalar to float*), align 4
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; PTX: ld.shared.f32 %f{{[0-9]+}}, [scalar];
; store cast
store float %v, float* addrspacecast (float addrspace(3)* @scalar to float*), align 4
; PTX: st.shared.f32 [scalar], %f{{[0-9]+}};
; use syncthreads to disable optimizations across components
call void @llvm.cuda.syncthreads()
; PTX: bar.sync 0;
; cast; load
%2 = addrspacecast float addrspace(3)* @scalar to float*
[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
%3 = load float, float* %2, align 4
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; PTX: ld.shared.f32 %f{{[0-9]+}}, [scalar];
; cast; store
store float %v, float* %2, align 4
; PTX: st.shared.f32 [scalar], %f{{[0-9]+}};
call void @llvm.cuda.syncthreads()
; PTX: bar.sync 0;
; load gep cast
[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
%4 = load float, float* getelementptr inbounds ([10 x float]* addrspacecast ([10 x float] addrspace(3)* @array to [10 x float]*), i32 0, i32 5), align 4
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; PTX: ld.shared.f32 %f{{[0-9]+}}, [array+20];
; store gep cast
store float %v, float* getelementptr inbounds ([10 x float]* addrspacecast ([10 x float] addrspace(3)* @array to [10 x float]*), i32 0, i32 5), align 4
; PTX: st.shared.f32 [array+20], %f{{[0-9]+}};
call void @llvm.cuda.syncthreads()
; PTX: bar.sync 0;
; gep cast; load
[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
%5 = getelementptr inbounds [10 x float], [10 x float]* addrspacecast ([10 x float] addrspace(3)* @array to [10 x float]*), i32 0, i32 5
[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
%6 = load float, float* %5, align 4
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; PTX: ld.shared.f32 %f{{[0-9]+}}, [array+20];
; gep cast; store
store float %v, float* %5, align 4
; PTX: st.shared.f32 [array+20], %f{{[0-9]+}};
call void @llvm.cuda.syncthreads()
; PTX: bar.sync 0;
; cast; gep; load
%7 = addrspacecast [10 x float] addrspace(3)* @array to [10 x float]*
[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
%8 = getelementptr inbounds [10 x float], [10 x float]* %7, i32 0, i32 %i
[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
%9 = load float, float* %8, align 4
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; PTX: ld.shared.f32 %f{{[0-9]+}}, [%{{(r|rl|rd)[0-9]+}}];
; cast; gep; store
store float %v, float* %8, align 4
; PTX: st.shared.f32 [%{{(r|rl|rd)[0-9]+}}], %f{{[0-9]+}};
call void @llvm.cuda.syncthreads()
; PTX: bar.sync 0;
%sum2 = fadd float %1, %3
%sum3 = fadd float %sum2, %4
%sum4 = fadd float %sum3, %6
%sum5 = fadd float %sum4, %9
ret float %sum5
}
Canonicalize addrspacecast ConstExpr between different pointer types As a follow-up to r210375 which canonicalizes addrspacecast instructions, this patch canonicalizes addrspacecast constant expressions. Given clang uses ConstantExpr::getAddrSpaceCast to emit addrspacecast cosntant expressions, this patch is also a step towards having the frontend emit canonicalized addrspacecasts. Piggyback a minor refactor in InstCombineCasts.cpp Update three affected tests in addrspacecast-alias.ll, access-non-generic.ll and constant-fold-gep.ll and added one new test in constant-fold-address-space-pointer.ll llvm-svn: 211004
2014-06-16 05:40:57 +08:00
; When hoisting an addrspacecast between different pointer types, replace the
; addrspacecast with a bitcast.
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
define i32 @ld_int_from_float() {
; IR-LABEL: @ld_int_from_float
[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
; IR: load i32, i32 addrspace(3)* bitcast (float addrspace(3)* @scalar to i32 addrspace(3)*)
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
; PTX-LABEL: ld_int_from_float(
Canonicalize addrspacecast ConstExpr between different pointer types As a follow-up to r210375 which canonicalizes addrspacecast instructions, this patch canonicalizes addrspacecast constant expressions. Given clang uses ConstantExpr::getAddrSpaceCast to emit addrspacecast cosntant expressions, this patch is also a step towards having the frontend emit canonicalized addrspacecasts. Piggyback a minor refactor in InstCombineCasts.cpp Update three affected tests in addrspacecast-alias.ll, access-non-generic.ll and constant-fold-gep.ll and added one new test in constant-fold-address-space-pointer.ll llvm-svn: 211004
2014-06-16 05:40:57 +08:00
; PTX: ld.shared.u{{(32|64)}}
[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
%1 = load i32, i32* addrspacecast(float addrspace(3)* @scalar to i32*), align 4
Optimize away unnecessary address casts. Removes unnecessary casts from non-generic address spaces to the generic address space for certain code patterns. Patch by Jingyue Wu. llvm-svn: 205571
2014-04-04 05:18:25 +08:00
ret i32 %1
}
declare void @llvm.cuda.syncthreads() #3
attributes #3 = { noduplicate nounwind }