llvm-project/llvm/test/CodeGen/AMDGPU/ctpop.ll

301 lines
10 KiB
LLVM
Raw Normal View History

; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC -check-prefix=VI %s
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
declare i32 @llvm.ctpop.i32(i32) nounwind readnone
declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32>) nounwind readnone
declare <4 x i32> @llvm.ctpop.v4i32(<4 x i32>) nounwind readnone
declare <8 x i32> @llvm.ctpop.v8i32(<8 x i32>) nounwind readnone
declare <16 x i32> @llvm.ctpop.v16i32(<16 x i32>) nounwind readnone
; FUNC-LABEL: {{^}}s_ctpop_i32:
; GCN: s_load_dword [[SVAL:s[0-9]+]],
; GCN: s_bcnt1_i32_b32 [[SRESULT:s[0-9]+]], [[SVAL]]
; GCN: v_mov_b32_e32 [[VRESULT:v[0-9]+]], [[SRESULT]]
; GCN: buffer_store_dword [[VRESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @s_ctpop_i32(i32 addrspace(1)* noalias %out, i32 %val) nounwind {
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
store i32 %ctpop, i32 addrspace(1)* %out, align 4
ret void
}
; XXX - Why 0 in register?
; FUNC-LABEL: {{^}}v_ctpop_i32:
; GCN: buffer_load_dword [[VAL:v[0-9]+]],
; GCN: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], 0
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @v_ctpop_i32(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
store i32 %ctpop, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_add_chain_i32:
; GCN: buffer_load_dword [[VAL1:v[0-9]+]],
; GCN: buffer_load_dword [[VAL0:v[0-9]+]],
; GCN: v_bcnt_u32_b32_e64 [[MIDRESULT:v[0-9]+]], [[VAL1]], 0
; SI: v_bcnt_u32_b32_e32 [[RESULT:v[0-9]+]], [[VAL0]], [[MIDRESULT]]
; VI: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL0]], [[MIDRESULT]]
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
; EG: BCNT_INT
define void @v_ctpop_add_chain_i32(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in0, i32 addrspace(1)* noalias %in1) nounwind {
%val0 = load i32, i32 addrspace(1)* %in0, align 4
%val1 = load i32, i32 addrspace(1)* %in1, align 4
%ctpop0 = call i32 @llvm.ctpop.i32(i32 %val0) nounwind readnone
%ctpop1 = call i32 @llvm.ctpop.i32(i32 %val1) nounwind readnone
%add = add i32 %ctpop0, %ctpop1
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_add_sgpr_i32:
; GCN: buffer_load_dword [[VAL0:v[0-9]+]],
; GCN: s_waitcnt
; GCN-NEXT: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL0]], s{{[0-9]+}}
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
define void @v_ctpop_add_sgpr_i32(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in0, i32 addrspace(1)* noalias %in1, i32 %sval) nounwind {
%val0 = load i32, i32 addrspace(1)* %in0, align 4
%ctpop0 = call i32 @llvm.ctpop.i32(i32 %val0) nounwind readnone
%add = add i32 %ctpop0, %sval
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_v2i32:
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: s_endpgm
; EG: BCNT_INT
; EG: BCNT_INT
define void @v_ctpop_v2i32(<2 x i32> addrspace(1)* noalias %out, <2 x i32> addrspace(1)* noalias %in) nounwind {
%val = load <2 x i32>, <2 x i32> addrspace(1)* %in, align 8
%ctpop = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> %val) nounwind readnone
store <2 x i32> %ctpop, <2 x i32> addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_v4i32:
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: s_endpgm
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
define void @v_ctpop_v4i32(<4 x i32> addrspace(1)* noalias %out, <4 x i32> addrspace(1)* noalias %in) nounwind {
%val = load <4 x i32>, <4 x i32> addrspace(1)* %in, align 16
%ctpop = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %val) nounwind readnone
store <4 x i32> %ctpop, <4 x i32> addrspace(1)* %out, align 16
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_v8i32:
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: s_endpgm
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
define void @v_ctpop_v8i32(<8 x i32> addrspace(1)* noalias %out, <8 x i32> addrspace(1)* noalias %in) nounwind {
%val = load <8 x i32>, <8 x i32> addrspace(1)* %in, align 32
%ctpop = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> %val) nounwind readnone
store <8 x i32> %ctpop, <8 x i32> addrspace(1)* %out, align 32
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_v16i32:
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: v_bcnt_u32_b32_e64
; GCN: s_endpgm
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
; EG: BCNT_INT
define void @v_ctpop_v16i32(<16 x i32> addrspace(1)* noalias %out, <16 x i32> addrspace(1)* noalias %in) nounwind {
%val = load <16 x i32>, <16 x i32> addrspace(1)* %in, align 32
%ctpop = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %val) nounwind readnone
store <16 x i32> %ctpop, <16 x i32> addrspace(1)* %out, align 32
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_i32_add_inline_constant:
; GCN: buffer_load_dword [[VAL:v[0-9]+]],
; GCN: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], 4
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @v_ctpop_i32_add_inline_constant(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
%add = add i32 %ctpop, 4
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_i32_add_inline_constant_inv:
; GCN: buffer_load_dword [[VAL:v[0-9]+]],
; GCN: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], 4
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @v_ctpop_i32_add_inline_constant_inv(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
%add = add i32 4, %ctpop
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_i32_add_literal:
; GCN-DAG: buffer_load_dword [[VAL:v[0-9]+]],
; GCN-DAG: v_mov_b32_e32 [[LIT:v[0-9]+]], 0x1869f
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: v_bcnt_u32_b32_e32 [[RESULT:v[0-9]+]], [[VAL]], [[LIT]]
; VI: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], [[LIT]]
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
define void @v_ctpop_i32_add_literal(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
%add = add i32 %ctpop, 99999
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_i32_add_var:
; GCN-DAG: buffer_load_dword [[VAL:v[0-9]+]],
; GCN-DAG: s_load_dword [[VAR:s[0-9]+]],
; GCN: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], [[VAR]]
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @v_ctpop_i32_add_var(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in, i32 %const) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
%add = add i32 %ctpop, %const
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_i32_add_var_inv:
; GCN-DAG: buffer_load_dword [[VAL:v[0-9]+]],
; GCN-DAG: s_load_dword [[VAR:s[0-9]+]],
; GCN: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], [[VAR]]
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @v_ctpop_i32_add_var_inv(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in, i32 %const) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
%add = add i32 %const, %ctpop
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_ctpop_i32_add_vvar_inv:
; GCN-DAG: buffer_load_dword [[VAL:v[0-9]+]], off, s[{{[0-9]+:[0-9]+}}], {{0$}}
; GCN-DAG: buffer_load_dword [[VAR:v[0-9]+]], off, s[{{[0-9]+:[0-9]+}}], 0 offset:16
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: v_bcnt_u32_b32_e32 [[RESULT:v[0-9]+]], [[VAL]], [[VAR]]
; VI: v_bcnt_u32_b32_e64 [[RESULT:v[0-9]+]], [[VAL]], [[VAR]]
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @v_ctpop_i32_add_vvar_inv(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %in, i32 addrspace(1)* noalias %constptr) nounwind {
%val = load i32, i32 addrspace(1)* %in, align 4
%ctpop = call i32 @llvm.ctpop.i32(i32 %val) nounwind readnone
[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
%gep = getelementptr i32, i32 addrspace(1)* %constptr, i32 4
%const = load i32, i32 addrspace(1)* %gep, align 4
%add = add i32 %const, %ctpop
store i32 %add, i32 addrspace(1)* %out, align 4
ret void
}
; FIXME: We currently disallow SALU instructions in all branches,
; but there are some cases when the should be allowed.
; FUNC-LABEL: {{^}}ctpop_i32_in_br:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xd
; VI: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x34
; GCN: s_bcnt1_i32_b32 [[SRESULT:s[0-9]+]], [[VAL]]
; GCN: v_mov_b32_e32 [[RESULT]], [[SRESULT]]
; GCN: buffer_store_dword [[RESULT]],
; GCN: s_endpgm
; EG: BCNT_INT
define void @ctpop_i32_in_br(i32 addrspace(1)* %out, i32 addrspace(1)* %in, i32 %ctpop_arg, i32 %cond) {
entry:
%tmp0 = icmp eq i32 %cond, 0
br i1 %tmp0, label %if, label %else
if:
%tmp2 = call i32 @llvm.ctpop.i32(i32 %ctpop_arg)
br label %endif
else:
[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
%tmp3 = getelementptr i32, i32 addrspace(1)* %in, i32 1
%tmp4 = load i32, i32 addrspace(1)* %tmp3
br label %endif
endif:
%tmp5 = phi i32 [%tmp2, %if], [%tmp4, %else]
store i32 %tmp5, i32 addrspace(1)* %out
ret void
}