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/bswap.ll

118 lines
4.2 KiB
LLVM
Raw Normal View History

AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
declare i32 @llvm.bswap.i32(i32) nounwind readnone
declare <2 x i32> @llvm.bswap.v2i32(<2 x i32>) nounwind readnone
declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>) nounwind readnone
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
declare <8 x i32> @llvm.bswap.v8i32(<8 x i32>) nounwind readnone
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
declare i64 @llvm.bswap.i64(i64) nounwind readnone
declare <2 x i64> @llvm.bswap.v2i64(<2 x i64>) nounwind readnone
declare <4 x i64> @llvm.bswap.v4i64(<4 x i64>) nounwind readnone
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
; FUNC-LABEL: @test_bswap_i32
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: buffer_load_dword [[VAL:v[0-9]+]]
; SI-DAG: v_alignbit_b32 [[TMP0:v[0-9]+]], [[VAL]], [[VAL]], 8
; SI-DAG: v_alignbit_b32 [[TMP1:v[0-9]+]], [[VAL]], [[VAL]], 24
; SI-DAG: s_mov_b32 [[K:s[0-9]+]], 0xff00ff
; SI: v_bfi_b32 [[RESULT:v[0-9]+]], [[K]], [[TMP1]], [[TMP0]]
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
define void @test_bswap_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) nounwind {
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load i32, i32 addrspace(1)* %in, align 4
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
%bswap = call i32 @llvm.bswap.i32(i32 %val) nounwind readnone
store i32 %bswap, i32 addrspace(1)* %out, align 4
ret void
}
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
; FUNC-LABEL: @test_bswap_v2i32
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI: s_endpgm
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
define void @test_bswap_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) nounwind {
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load <2 x i32>, <2 x i32> addrspace(1)* %in, align 8
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
%bswap = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> %val) nounwind readnone
store <2 x i32> %bswap, <2 x i32> addrspace(1)* %out, align 8
ret void
}
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
; FUNC-LABEL: @test_bswap_v4i32
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI: s_endpgm
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
define void @test_bswap_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) nounwind {
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load <4 x i32>, <4 x i32> addrspace(1)* %in, align 16
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
%bswap = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %val) nounwind readnone
store <4 x i32> %bswap, <4 x i32> addrspace(1)* %out, align 16
ret void
}
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
; FUNC-LABEL: @test_bswap_v8i32
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_alignbit_b32
; SI-DAG: v_bfi_b32
; SI: s_endpgm
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
define void @test_bswap_v8i32(<8 x i32> addrspace(1)* %out, <8 x i32> addrspace(1)* %in) nounwind {
[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
%val = load <8 x i32>, <8 x i32> addrspace(1)* %in, align 32
R600/SI: Add pattern for bswap llvm-svn: 220304
2014-10-22 00:25:08 +08:00
%bswap = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> %val) nounwind readnone
store <8 x i32> %bswap, <8 x i32> addrspace(1)* %out, align 32
ret void
}
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; FUNC-LABEL: {{^}}test_bswap_i64:
; SI-NOT: v_or_b32_e64 v{{[0-9]+}}, 0, 0
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
define void @test_bswap_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %in) nounwind {
[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
%val = load i64, i64 addrspace(1)* %in, align 8
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
%bswap = call i64 @llvm.bswap.i64(i64 %val) nounwind readnone
store i64 %bswap, i64 addrspace(1)* %out, align 8
ret void
}
define void @test_bswap_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %in) nounwind {
[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
%val = load <2 x i64>, <2 x i64> addrspace(1)* %in, align 16
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
%bswap = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> %val) nounwind readnone
store <2 x i64> %bswap, <2 x i64> addrspace(1)* %out, align 16
ret void
}
define void @test_bswap_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> addrspace(1)* %in) nounwind {
[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
%val = load <4 x i64>, <4 x i64> addrspace(1)* %in, align 32
R600: Fix selection failure for vector bswap llvm-svn: 210475
2014-06-10 00:20:25 +08:00
%bswap = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> %val) nounwind readnone
store <4 x i64> %bswap, <4 x i64> addrspace(1)* %out, align 32
ret void
}