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

147 lines
7.2 KiB
LLVM
Raw Normal View History

; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx906 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX906 -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=cedar -verify-machineinstrs < %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=juniper -verify-machineinstrs < %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood -verify-machineinstrs < %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=sumo -verify-machineinstrs < %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=barts -verify-machineinstrs < %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=caicos -verify-machineinstrs < %s
; RUN: not llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=turks -verify-machineinstrs < %s
2014-06-26 09:28:05 +08:00
declare float @llvm.fma.f32(float, float, float) nounwind readnone
declare <2 x float> @llvm.fma.v2f32(<2 x float>, <2 x float>, <2 x float>) nounwind readnone
declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
; FUNC-LABEL: {{^}}fma_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_fma_f32 {{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}
; GFX906: v_fmac_f32_e32 {{v[0-9]+, v[0-9]+, v[0-9]+}}
; EG: MEM_RAT_{{.*}} STORE_{{.*}} [[RES:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}},
; EG: FMA {{\*? *}}[[RES]]
define amdgpu_kernel void @fma_f32(float addrspace(1)* %out, float addrspace(1)* %in1,
float addrspace(1)* %in2, float addrspace(1)* %in3) {
%r0 = load float, float addrspace(1)* %in1
%r1 = load float, float addrspace(1)* %in2
%r2 = load float, float addrspace(1)* %in3
%r3 = tail call float @llvm.fma.f32(float %r0, float %r1, float %r2)
store float %r3, float addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fmac_to_3addr_f32:
; GCN: v_fma_f32 {{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}
define float @fmac_to_3addr_f32(float %r0, float %r1, float %r2) {
%r3 = tail call float @llvm.fma.f32(float %r0, float %r1, float %r2)
ret float %r3
}
; FUNC-LABEL: {{^}}fma_v2f32:
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_fma_f32
; SI: v_fma_f32
; GFX906: v_fma_f32 {{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}
; GFX906: v_fmac_f32_e32 {{v[0-9]+, v[0-9]+, v[0-9]+}}
; EG: MEM_RAT_{{.*}} STORE_{{.*}} [[RES:T[0-9]]].[[CHLO:[XYZW]]][[CHHI:[XYZW]]], {{T[0-9]\.[XYZW]}},
; EG-DAG: FMA {{\*? *}}[[RES]].[[CHLO]]
; EG-DAG: FMA {{\*? *}}[[RES]].[[CHHI]]
define amdgpu_kernel void @fma_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in1,
2014-06-26 09:28:05 +08:00
<2 x float> addrspace(1)* %in2, <2 x float> addrspace(1)* %in3) {
%r0 = load <2 x float>, <2 x float> addrspace(1)* %in1
%r1 = load <2 x float>, <2 x float> addrspace(1)* %in2
%r2 = load <2 x float>, <2 x float> addrspace(1)* %in3
%r3 = tail call <2 x float> @llvm.fma.v2f32(<2 x float> %r0, <2 x float> %r1, <2 x float> %r2)
store <2 x float> %r3, <2 x float> addrspace(1)* %out
ret void
2014-06-26 09:28:05 +08:00
}
; FUNC-LABEL: {{^}}fma_v4f32:
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_fma_f32
; SI: v_fma_f32
; SI: v_fma_f32
; SI: v_fma_f32
; GFX906: v_fma_f32 {{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}
; GFX906: v_fma_f32 {{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}
; GFX906: v_fma_f32 {{v[0-9]+, v[0-9]+, v[0-9]+, v[0-9]+}}
AMDGPU: Add pass to lower kernel arguments to loads This replaces most argument uses with loads, but for now not all. The code in SelectionDAG for calling convention lowering is actively harmful for amdgpu_kernel. It attempts to split the argument types into register legal types, which results in low quality code for arbitary types. Since all kernel arguments are passed in memory, we just want the raw types. I've tried a couple of methods of mitigating this in SelectionDAG, but it's easier to just bypass this problem alltogether. It's possible to hack around the problem in the initial lowering, but the real problem is the DAG then expects to be able to use CopyToReg/CopyFromReg for uses of the arguments outside the block. Exposing the argument loads in the IR also has the advantage that the LoadStoreVectorizer can merge them. I'm not sure the best approach to dealing with the IR argument list is. The patch as-is just leaves the IR arguments in place, so all the existing code will still compute the same kernarg size and pointlessly lowers the arguments. Arguably the frontend should emit kernels with an empty argument list in the first place. Alternatively a dummy array could be inserted as a single argument just to reserve space. This does have some disadvantages. Local pointer kernel arguments can no longer have AssertZext placed on them as the equivalent !range metadata is not valid on pointer typed loads. This is mostly bad for SI which needs to know about the known bits in order to use the DS instruction offset, so in this case this is not done. More importantly, this skips noalias arguments since this pass does not yet convert this to the equivalent !alias.scope and !noalias metadata. Producing this metadata correctly seems to be tricky, although this logically is the same as inlining into a function which doesn't exist. Additionally, exposing these loads to the vectorizer may result in degraded aliasing information if a pointer load is merged with another argument load. I'm also not entirely sure this is preserving the current clover ABI, although I would greatly prefer if it would stop widening arguments and match the HSA ABI. As-is I think it is extending < 4-byte arguments to 4-bytes but doesn't align them to 4-bytes. llvm-svn: 335650
2018-06-27 03:10:00 +08:00
; GFX906: v_fmac_f32_e32 {{v[0-9]+, v[0-9]+, v[0-9]+$}}
; EG: MEM_RAT_{{.*}} STORE_{{.*}} [[RES:T[0-9]]].{{[XYZW][XYZW][XYZW][XYZW]}}, {{T[0-9]\.[XYZW]}},
; EG-DAG: FMA {{\*? *}}[[RES]].X
; EG-DAG: FMA {{\*? *}}[[RES]].Y
; EG-DAG: FMA {{\*? *}}[[RES]].Z
; EG-DAG: FMA {{\*? *}}[[RES]].W
define amdgpu_kernel void @fma_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in1,
2014-06-26 09:28:05 +08:00
<4 x float> addrspace(1)* %in2, <4 x float> addrspace(1)* %in3) {
%r0 = load <4 x float>, <4 x float> addrspace(1)* %in1
%r1 = load <4 x float>, <4 x float> addrspace(1)* %in2
%r2 = load <4 x float>, <4 x float> addrspace(1)* %in3
%r3 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %r0, <4 x float> %r1, <4 x float> %r2)
store <4 x float> %r3, <4 x float> addrspace(1)* %out
ret void
}
; FUNC-LABEL: @fma_commute_mul_inline_imm_f32
; SI: v_fma_f32 {{v[0-9]+}}, {{v[0-9]+}}, 2.0, {{v[0-9]+}}
define amdgpu_kernel void @fma_commute_mul_inline_imm_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) nounwind {
%tid = tail call i32 @llvm.r600.read.tidig.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
%in.a.gep = getelementptr float, float addrspace(1)* %in.a, i32 %tid
%in.b.gep = getelementptr float, float addrspace(1)* %in.b, i32 %tid
%out.gep = getelementptr float, float addrspace(1)* %out, i32 %tid
%a = load float, float addrspace(1)* %in.a.gep, align 4
%b = load float, float addrspace(1)* %in.b.gep, align 4
%fma = call float @llvm.fma.f32(float %a, float 2.0, float %b)
store float %fma, float addrspace(1)* %out.gep, align 4
ret void
}
; FUNC-LABEL: @fma_commute_mul_s_f32
define amdgpu_kernel void @fma_commute_mul_s_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b, float %b) nounwind {
%tid = tail call i32 @llvm.r600.read.tidig.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
%in.a.gep = getelementptr float, float addrspace(1)* %in.a, i32 %tid
%in.b.gep = getelementptr float, float addrspace(1)* %in.b, i32 %tid
%out.gep = getelementptr float, float addrspace(1)* %out, i32 %tid
%a = load float, float addrspace(1)* %in.a.gep, align 4
%c = load float, float addrspace(1)* %in.b.gep, align 4
%fma = call float @llvm.fma.f32(float %a, float %b, float %c)
store float %fma, float addrspace(1)* %out.gep, align 4
ret void
2014-06-26 09:28:05 +08:00
}
; Without special casing the inline constant check for v_fmac_f32's
; src2, this fails to fold the 1.0 into an fma.
; FUNC-LABEL: {{^}}fold_inline_imm_into_fmac_src2_f32:
; GFX906: {{buffer|flat|global}}_load_dword [[A:v[0-9]+]]
; GFX906: {{buffer|flat|global}}_load_dword [[B:v[0-9]+]]
; GFX906: v_add_f32_e32 [[TMP2:v[0-9]+]], [[A]], [[A]]
; GFX906: v_fma_f32 v{{[0-9]+}}, [[TMP2]], -4.0, 1.0
define amdgpu_kernel void @fold_inline_imm_into_fmac_src2_f32(float addrspace(1)* %out, float addrspace(1)* %a, float addrspace(1)* %b) nounwind {
bb:
%tid = call i32 @llvm.r600.read.tidig.x()
%tid.ext = sext i32 %tid to i64
%gep.a = getelementptr inbounds float, float addrspace(1)* %a, i64 %tid.ext
%gep.b = getelementptr inbounds float, float addrspace(1)* %b, i64 %tid.ext
%gep.out = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
%tmp = load volatile float, float addrspace(1)* %gep.a
%tmp1 = load volatile float, float addrspace(1)* %gep.b
%tmp2 = fadd contract float %tmp, %tmp
%tmp3 = fmul contract float %tmp2, 4.0
%tmp4 = fsub contract float 1.0, %tmp3
%tmp5 = fadd contract float %tmp4, %tmp1
%tmp6 = fadd contract float %tmp1, %tmp1
%tmp7 = fmul contract float %tmp6, %tmp
%tmp8 = fsub contract float 1.0, %tmp7
%tmp9 = fmul contract float %tmp8, 8.0
%tmp10 = fadd contract float %tmp5, %tmp9
store float %tmp10, float addrspace(1)* %gep.out
ret void
}