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/combine_vloads.ll

43 lines
2.0 KiB
LLVM
Raw Normal View History

AMDGPU: Remove remnants of old address space mapping llvm-svn: 341165
2018-08-31 13:49:54 +08:00
; RUN: llc -march=r600 -mtriple=r600-- -mcpu=cypress < %s | FileCheck -check-prefix=EG %s
Add target hook to prevent folding some bitcasted loads. This is to avoid this transformation in some cases: fold (conv (load x)) -> (load (conv*)x) On architectures that don't natively support some vector loads efficiently casting the load to a smaller vector of larger types and loading is more efficient. Patch by Micah Villmow. llvm-svn: 194783
2013-11-15 12:42:23 +08:00
;
[AMDGPU] Fix pointer info for lowering load/store for r600 for amdgiz environment r600 uses dummy pointer info for lowering load/store. Since dummy pointer info assumes address space 0, this causes isel failure when temporary load/store SDNodes are generated for amdgiz environment. Since the offest is not constant, FixedStack pseudo source value cannot be used to create the pointer info. This patch creates pointer info using llvm undef value. At least this provides correct address space so that isel can be done correctly. Differential Revision: https://reviews.llvm.org/D39698 llvm-svn: 317862
2017-11-10 10:03:28 +08:00
; kernel void combine_vloads(global char8 addrspace(5)* src, global char8 addrspace(5)* result) {
Add target hook to prevent folding some bitcasted loads. This is to avoid this transformation in some cases: fold (conv (load x)) -> (load (conv*)x) On architectures that don't natively support some vector loads efficiently casting the load to a smaller vector of larger types and loading is more efficient. Patch by Micah Villmow. llvm-svn: 194783
2013-11-15 12:42:23 +08:00
; for (int i = 0; i < 1024; ++i)
; result[i] = src[0] + src[1] + src[2] + src[3];
; }
;
; 128-bit loads instead of many 8-bit
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; EG-LABEL: {{^}}combine_vloads:
Add target hook to prevent folding some bitcasted loads. This is to avoid this transformation in some cases: fold (conv (load x)) -> (load (conv*)x) On architectures that don't natively support some vector loads efficiently casting the load to a smaller vector of larger types and loading is more efficient. Patch by Micah Villmow. llvm-svn: 194783
2013-11-15 12:42:23 +08:00
; EG: VTX_READ_128
; EG: VTX_READ_128
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @combine_vloads(<8 x i8> addrspace(1)* nocapture %src, <8 x i8> addrspace(1)* nocapture %result) nounwind {
Add target hook to prevent folding some bitcasted loads. This is to avoid this transformation in some cases: fold (conv (load x)) -> (load (conv*)x) On architectures that don't natively support some vector loads efficiently casting the load to a smaller vector of larger types and loading is more efficient. Patch by Micah Villmow. llvm-svn: 194783
2013-11-15 12:42:23 +08:00
entry:
br label %for.body
for.exit: ; preds = %for.body
ret void
for.body: ; preds = %for.body, %entry
%i.01 = phi i32 [ 0, %entry ], [ %tmp19, %for.body ]
%arrayidx_v4 = bitcast <8 x i8> addrspace(1)* %src to <32 x i8> addrspace(1)*
%0 = bitcast <32 x i8> addrspace(1)* %arrayidx_v4 to <8 x i32> addrspace(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
%vecload2 = load <8 x i32>, <8 x i32> addrspace(1)* %0, align 32
Add target hook to prevent folding some bitcasted loads. This is to avoid this transformation in some cases: fold (conv (load x)) -> (load (conv*)x) On architectures that don't natively support some vector loads efficiently casting the load to a smaller vector of larger types and loading is more efficient. Patch by Micah Villmow. llvm-svn: 194783
2013-11-15 12:42:23 +08:00
%1 = bitcast <8 x i32> %vecload2 to <32 x i8>
%tmp5 = shufflevector <32 x i8> %1, <32 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%tmp8 = shufflevector <32 x i8> %1, <32 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%tmp9 = add nsw <8 x i8> %tmp5, %tmp8
%tmp12 = shufflevector <32 x i8> %1, <32 x i8> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
%tmp13 = add nsw <8 x i8> %tmp9, %tmp12
%tmp16 = shufflevector <32 x i8> %1, <32 x i8> undef, <8 x i32> <i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
%tmp17 = add nsw <8 x i8> %tmp13, %tmp16
[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
%scevgep = getelementptr <8 x i8>, <8 x i8> addrspace(1)* %result, i32 %i.01
Add target hook to prevent folding some bitcasted loads. This is to avoid this transformation in some cases: fold (conv (load x)) -> (load (conv*)x) On architectures that don't natively support some vector loads efficiently casting the load to a smaller vector of larger types and loading is more efficient. Patch by Micah Villmow. llvm-svn: 194783
2013-11-15 12:42:23 +08:00
%2 = bitcast <8 x i8> %tmp17 to <2 x i32>
%3 = bitcast <8 x i8> addrspace(1)* %scevgep to <2 x i32> addrspace(1)*
store <2 x i32> %2, <2 x i32> addrspace(1)* %3, align 8
%tmp19 = add nsw i32 %i.01, 1
%exitcond = icmp eq i32 %tmp19, 1024
br i1 %exitcond, label %for.exit, label %for.body
}