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/rsq.ll

139 lines
5.7 KiB
LLVM
Raw Normal View History

AMDGPU: Remove some old intrinsic uses from tests llvm-svn: 260493
2016-02-11 14:02:01 +08:00
; RUN: llc -march=amdgcn -mattr=-fp32-denormals -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=SI-UNSAFE -check-prefix=SI %s
; RUN: llc -march=amdgcn -mattr=-fp32-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=SI-SAFE -check-prefix=SI %s
R600/SI: Match rsq instructions llvm-svn: 210226
2014-06-05 08:15:55 +08:00
AMDGPU: Remove some old intrinsic uses from tests llvm-svn: 260493
2016-02-11 14:02:01 +08:00
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
R600/SI: Match rsq instructions llvm-svn: 210226
2014-06-05 08:15:55 +08:00
declare float @llvm.sqrt.f32(float) nounwind readnone
declare double @llvm.sqrt.f64(double) nounwind readnone
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}rsq_f32:
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_rsq_f32_e32
; SI: s_endpgm
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 @rsq_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load float, float addrspace(1)* %in, align 4
R600/SI: Match rsq instructions llvm-svn: 210226
2014-06-05 08:15:55 +08:00
%sqrt = call float @llvm.sqrt.f32(float %val) nounwind readnone
%div = fdiv float 1.0, %sqrt
store float %div, float addrspace(1)* %out, align 4
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}rsq_f64:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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-UNSAFE: v_rsq_f64_e32
; SI-SAFE: v_sqrt_f64_e32
; SI: s_endpgm
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 @rsq_f64(double addrspace(1)* noalias %out, double addrspace(1)* noalias %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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load double, double addrspace(1)* %in, align 4
R600/SI: Match rsq instructions llvm-svn: 210226
2014-06-05 08:15:55 +08:00
%sqrt = call double @llvm.sqrt.f64(double %val) nounwind readnone
%div = fdiv double 1.0, %sqrt
store double %div, double addrspace(1)* %out, align 4
ret void
}
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. llvm-svn: 217789
2014-09-16 01:15:02 +08:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; SI-LABEL: {{^}}rsq_f32_sgpr:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" 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_rsq_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
; SI: s_endpgm
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 @rsq_f32_sgpr(float addrspace(1)* noalias %out, float %val) nounwind {
R600/SI: Prefer selecting more e64 instruction forms. Add some more tests to make sure better operand choices are still made. Leave some cases that seem to have no reason to ever be e64 alone. llvm-svn: 217789
2014-09-16 01:15:02 +08:00
%sqrt = call float @llvm.sqrt.f32(float %val) nounwind readnone
%div = fdiv float 1.0, %sqrt
store float %div, float addrspace(1)* %out, align 4
ret void
}
R600: Implement getRsqrtEstimate Only do for f32 since I'm unclear on both what this is expecting for the refinement steps in terms of accuracy, and what f64 instruction actually provides. llvm-svn: 225827
2015-01-14 04:53:18 +08:00
; Recognize that this is rsqrt(a) * rcp(b) * c,
; not 1 / ( 1 / sqrt(a)) * rcp(b) * c.
; SI-LABEL: @rsqrt_fmul
; SI-DAG: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
; SI-DAG: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
; SI-DAG: buffer_load_dword [[C:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:8
; SI-UNSAFE-DAG: v_rsq_f32_e32 [[RSQA:v[0-9]+]], [[A]]
; SI-UNSAFE-DAG: v_rcp_f32_e32 [[RCPB:v[0-9]+]], [[B]]
; SI-UNSAFE-DAG: v_mul_f32_e32 [[TMP:v[0-9]+]], [[RCPB]], [[RSQA]]
; SI-UNSAFE: v_mul_f32_e32 [[RESULT:v[0-9]+]], [[TMP]], [[C]]
; SI-UNSAFE: buffer_store_dword [[RESULT]]
; SI-SAFE-NOT: v_rsq_f32
; SI: s_endpgm
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 @rsqrt_fmul(float addrspace(1)* %out, float addrspace(1)* %in) {
AMDGPU: Remove some old intrinsic uses from tests llvm-svn: 260493
2016-02-11 14:02:01 +08:00
%tid = call i32 @llvm.amdgcn.workitem.id.x() 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
%out.gep = getelementptr float, float addrspace(1)* %out, i32 %tid
%gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
%gep.2 = getelementptr float, float addrspace(1)* %gep.0, i32 2
R600: Implement getRsqrtEstimate Only do for f32 since I'm unclear on both what this is expecting for the refinement steps in terms of accuracy, and what f64 instruction actually provides. llvm-svn: 225827
2015-01-14 04:53:18 +08:00
AMDGPU: Add volatile to test loads and stores When the memory vectorizer is enabled, these tests break. These tests don't really care about the memory instructions, and it's easier to write check lines with the unmerged loads. llvm-svn: 266071
2016-04-12 21:38:18 +08:00
%a = load volatile float, float addrspace(1)* %gep.0
%b = load volatile float, float addrspace(1)* %gep.1
%c = load volatile float, float addrspace(1)* %gep.2
R600: Implement getRsqrtEstimate Only do for f32 since I'm unclear on both what this is expecting for the refinement steps in terms of accuracy, and what f64 instruction actually provides. llvm-svn: 225827
2015-01-14 04:53:18 +08:00
%x = call float @llvm.sqrt.f32(float %a)
%y = fmul float %x, %b
%z = fdiv float %c, %y
store float %z, float addrspace(1)* %out.gep
ret void
}
AMDGPU: fdiv -1, x -> rcp -x llvm-svn: 277535
2016-08-03 06:25:04 +08:00
; SI-LABEL: {{^}}neg_rsq_f32:
; SI-SAFE: v_sqrt_f32_e32 [[SQRT:v[0-9]+]], v{{[0-9]+}}
; SI-SAFE: v_rcp_f32_e64 [[RSQ:v[0-9]+]], -[[SQRT]]
; SI-SAFE: buffer_store_dword [[RSQ]]
; SI-UNSAFE: v_rsq_f32_e32 [[RSQ:v[0-9]+]], v{{[0-9]+}}
; SI-UNSAFE: v_xor_b32_e32 [[NEG_RSQ:v[0-9]+]], 0x80000000, [[RSQ]]
; SI-UNSAFE: buffer_store_dword [[NEG_RSQ]]
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 @neg_rsq_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
AMDGPU: fdiv -1, x -> rcp -x llvm-svn: 277535
2016-08-03 06:25:04 +08:00
%val = load float, float addrspace(1)* %in, align 4
%sqrt = call float @llvm.sqrt.f32(float %val)
%div = fdiv float -1.0, %sqrt
store float %div, float addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}neg_rsq_f64:
; SI-SAFE: v_sqrt_f64_e32
; SI-SAFE: v_div_scale_f64
; SI-UNSAFE: v_sqrt_f64_e32 [[SQRT:v\[[0-9]+:[0-9]+\]]], v{{\[[0-9]+:[0-9]+\]}}
; SI-UNSAFE: v_rcp_f64_e64 [[RCP:v\[[0-9]+:[0-9]+\]]], -[[SQRT]]
; SI-UNSAFE: buffer_store_dwordx2 [[RCP]]
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 @neg_rsq_f64(double addrspace(1)* noalias %out, double addrspace(1)* noalias %in) nounwind {
AMDGPU: fdiv -1, x -> rcp -x llvm-svn: 277535
2016-08-03 06:25:04 +08:00
%val = load double, double addrspace(1)* %in, align 4
%sqrt = call double @llvm.sqrt.f64(double %val)
%div = fdiv double -1.0, %sqrt
store double %div, double addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}neg_rsq_neg_f32:
; SI-SAFE: v_sqrt_f32_e64 [[SQRT:v[0-9]+]], -v{{[0-9]+}}
; SI-SAFE: v_rcp_f32_e64 [[RSQ:v[0-9]+]], -[[SQRT]]
; SI-SAFE: buffer_store_dword [[RSQ]]
; SI-UNSAFE: v_rsq_f32_e64 [[RSQ:v[0-9]+]], -v{{[0-9]+}}
; SI-UNSAFE: v_xor_b32_e32 [[NEG_RSQ:v[0-9]+]], 0x80000000, [[RSQ]]
; SI-UNSAFE: buffer_store_dword [[NEG_RSQ]]
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 @neg_rsq_neg_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
AMDGPU: fdiv -1, x -> rcp -x llvm-svn: 277535
2016-08-03 06:25:04 +08:00
%val = load float, float addrspace(1)* %in, align 4
%val.fneg = fsub float -0.0, %val
%sqrt = call float @llvm.sqrt.f32(float %val.fneg)
%div = fdiv float -1.0, %sqrt
store float %div, float addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}neg_rsq_neg_f64:
; SI-SAFE: v_sqrt_f64_e64 v{{\[[0-9]+:[0-9]+\]}}, -v{{\[[0-9]+:[0-9]+\]}}
; SI-SAFE: v_div_scale_f64
; SI-UNSAFE: v_sqrt_f64_e64 [[SQRT:v\[[0-9]+:[0-9]+\]]], -v{{\[[0-9]+:[0-9]+\]}}
; SI-UNSAFE: v_rcp_f64_e64 [[RCP:v\[[0-9]+:[0-9]+\]]], -[[SQRT]]
; SI-UNSAFE: buffer_store_dwordx2 [[RCP]]
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 @neg_rsq_neg_f64(double addrspace(1)* noalias %out, double addrspace(1)* noalias %in) nounwind {
AMDGPU: fdiv -1, x -> rcp -x llvm-svn: 277535
2016-08-03 06:25:04 +08:00
%val = load double, double addrspace(1)* %in, align 4
%val.fneg = fsub double -0.0, %val
%sqrt = call double @llvm.sqrt.f64(double %val.fneg)
%div = fdiv double -1.0, %sqrt
store double %div, double addrspace(1)* %out, align 4
ret void
}