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/AMDGPU/unroll.ll

101 lines
2.8 KiB
LLVM
Raw Normal View History

R600/SI: Fix tests with triples in them Only set the triple from the command line options. Some of these were still testing SI features and using the old r600-- triple. llvm-svn: 238958
2015-06-04 04:04:05 +08:00
; RUN: opt -mtriple=amdgcn-- -loop-unroll -simplifycfg -sroa %s -S -o - | FileCheck %s
; RUN: opt -mtriple=r600-- -loop-unroll -simplifycfg -sroa %s -S -o - | FileCheck %s
R600: Unconditionally unroll loops that contain GEPs with alloca pointers Implement the getUnrollingPreferences() function for AMDGPUTargetTransformInfo so that loops that do address calculations on pointers derived from alloca are unconditionally unrolled. Unrolling these loops makes it more likely that SROA will be able to eliminate the allocas, which is a big win for R600 since memory allocated by alloca (private memory) is really slow. llvm-svn: 199916
2014-01-24 02:49:28 +08:00
; This test contains a simple loop that initializes an array declared in
; private memory. We want to make sure these kinds of loops are always
; unrolled, because private memory is slow.
[AMDGPU] Boost unroll threshold for loops reading local memory This is less important than increase threshold for private memory, but still brings performance improvements in a wide range of tests. Unrolling more for local memory serves three purposes: it allows to combine ds operations if offset becomes static, saves registers used for offsets in case of static offsets, and allows better lds latency hiding. Differential Revision: https://reviews.llvm.org/D31412 llvm-svn: 298948
2017-03-29 06:13:51 +08:00
; CHECK-LABEL: @private_memory
R600: Unconditionally unroll loops that contain GEPs with alloca pointers Implement the getUnrollingPreferences() function for AMDGPUTargetTransformInfo so that loops that do address calculations on pointers derived from alloca are unconditionally unrolled. Unrolling these loops makes it more likely that SROA will be able to eliminate the allocas, which is a big win for R600 since memory allocated by alloca (private memory) is really slow. llvm-svn: 199916
2014-01-24 02:49:28 +08:00
; CHECK-NOT: alloca
; CHECK: store i32 5, i32 addrspace(1)* %out
[AMDGPU] Boost unroll threshold for loops reading local memory This is less important than increase threshold for private memory, but still brings performance improvements in a wide range of tests. Unrolling more for local memory serves three purposes: it allows to combine ds operations if offset becomes static, saves registers used for offsets in case of static offsets, and allows better lds latency hiding. Differential Revision: https://reviews.llvm.org/D31412 llvm-svn: 298948
2017-03-29 06:13:51 +08:00
define amdgpu_kernel void @private_memory(i32 addrspace(1)* %out) {
R600: Unconditionally unroll loops that contain GEPs with alloca pointers Implement the getUnrollingPreferences() function for AMDGPUTargetTransformInfo so that loops that do address calculations on pointers derived from alloca are unconditionally unrolled. Unrolling these loops makes it more likely that SROA will be able to eliminate the allocas, which is a big win for R600 since memory allocated by alloca (private memory) is really slow. llvm-svn: 199916
2014-01-24 02:49:28 +08:00
entry:
%0 = alloca [32 x i32]
br label %loop.header
loop.header:
%counter = phi i32 [0, %entry], [%inc, %loop.inc]
br label %loop.body
loop.body:
[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 [32 x i32], [32 x i32]* %0, i32 0, i32 %counter
R600: Unconditionally unroll loops that contain GEPs with alloca pointers Implement the getUnrollingPreferences() function for AMDGPUTargetTransformInfo so that loops that do address calculations on pointers derived from alloca are unconditionally unrolled. Unrolling these loops makes it more likely that SROA will be able to eliminate the allocas, which is a big win for R600 since memory allocated by alloca (private memory) is really slow. llvm-svn: 199916
2014-01-24 02:49:28 +08:00
store i32 %counter, i32* %ptr
br label %loop.inc
loop.inc:
%inc = add i32 %counter, 1
%1 = icmp sge i32 %counter, 32
br i1 %1, label %exit, label %loop.header
exit:
[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
%2 = getelementptr [32 x i32], [32 x i32]* %0, 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
%3 = load i32, i32* %2
R600: Unconditionally unroll loops that contain GEPs with alloca pointers Implement the getUnrollingPreferences() function for AMDGPUTargetTransformInfo so that loops that do address calculations on pointers derived from alloca are unconditionally unrolled. Unrolling these loops makes it more likely that SROA will be able to eliminate the allocas, which is a big win for R600 since memory allocated by alloca (private memory) is really slow. llvm-svn: 199916
2014-01-24 02:49:28 +08:00
store i32 %3, i32 addrspace(1)* %out
ret void
}
[AMDGPU] Boost unroll threshold for loops reading local memory This is less important than increase threshold for private memory, but still brings performance improvements in a wide range of tests. Unrolling more for local memory serves three purposes: it allows to combine ds operations if offset becomes static, saves registers used for offsets in case of static offsets, and allows better lds latency hiding. Differential Revision: https://reviews.llvm.org/D31412 llvm-svn: 298948
2017-03-29 06:13:51 +08:00
; Check that loop is unrolled for local memory references
; CHECK-LABEL: @local_memory
; CHECK: getelementptr i32, i32 addrspace(1)* %out, i32 128
; CHECK-NEXT: store
; CHECK-NEXT: ret
define amdgpu_kernel void @local_memory(i32 addrspace(1)* %out, i32 addrspace(3)* %lds) {
entry:
br label %loop.header
loop.header:
%counter = phi i32 [0, %entry], [%inc, %loop.inc]
br label %loop.body
loop.body:
%ptr_lds = getelementptr i32, i32 addrspace(3)* %lds, i32 %counter
%val = load i32, i32 addrspace(3)* %ptr_lds
%ptr_out = getelementptr i32, i32 addrspace(1)* %out, i32 %counter
store i32 %val, i32 addrspace(1)* %ptr_out
br label %loop.inc
loop.inc:
%inc = add i32 %counter, 1
%cond = icmp sge i32 %counter, 128
br i1 %cond, label %exit, label %loop.header
exit:
ret void
}
[AMDGPU] Unroll more to eliminate phis and conditions Increase threshold to unroll a loop which contains an "if" statement whose condition defined by a PHI belonging to the loop. This may help to eliminate if region and potentially even PHI itself, saving on both divergence and registers used for the PHI. Add a small bonus for each of such "if" statements. Differential Revision: https://reviews.llvm.org/D31693 llvm-svn: 299779
2017-04-08 00:26:28 +08:00
; Check that a loop with if inside completely unrolled to eliminate phi and if
; CHECK-LABEL: @unroll_for_if
; CHECK: entry:
; CHECK-NEXT: getelementptr
; CHECK-NEXT: store
; CHECK-NEXT: getelementptr
; CHECK-NEXT: store
; CHECK-NOT: br
define amdgpu_kernel void @unroll_for_if(i32* %a) {
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc
%i1 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%and = and i32 %i1, 1
%tobool = icmp eq i32 %and, 0
br i1 %tobool, label %for.inc, label %if.then
if.then: ; preds = %for.body
%0 = sext i32 %i1 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %0
store i32 0, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i32 %i1, 1
%cmp = icmp ult i32 %inc, 48
br i1 %cmp, label %for.body, label %for.end
for.end: ; preds = %for.cond
ret void
}