2015-01-06 19:00:21 +01:00
|
|
|
; RUN: llc -march=amdgcn -mcpu=SI < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
2014-11-14 19:30:06 +01:00
|
|
|
|
|
|
|
|
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}v_test_imax_sge_i32:
|
2014-11-14 19:30:06 +01:00
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
define void @v_test_imax_sge_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = 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
2015-02-27 20:29:02 +01:00
|
|
|
%gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
|
2015-02-27 22:17:42 +01:00
|
|
|
%a = load i32, i32 addrspace(1)* %gep0, align 4
|
|
|
|
|
%b = load i32, i32 addrspace(1)* %gep1, align 4
|
2014-11-14 19:30:06 +01:00
|
|
|
%cmp = icmp sge i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %outgep, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}v_test_imax_sge_v4i32:
|
|
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
define void @v_test_imax_sge_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %aptr, <4 x i32> addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
|
|
|
%gep0 = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %out, i32 %tid
|
|
|
|
|
%a = load <4 x i32>, <4 x i32> addrspace(1)* %gep0, align 4
|
|
|
|
|
%b = load <4 x i32>, <4 x i32> addrspace(1)* %gep1, align 4
|
|
|
|
|
%cmp = icmp sge <4 x i32> %a, %b
|
|
|
|
|
%val = select <4 x i1> %cmp, <4 x i32> %a, <4 x i32> %b
|
|
|
|
|
store <4 x i32> %val, <4 x i32> addrspace(1)* %outgep, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2014-11-14 19:30:06 +01:00
|
|
|
; FUNC-LABEL: @s_test_imax_sge_i32
|
|
|
|
|
; SI: s_max_i32
|
|
|
|
|
define void @s_test_imax_sge_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
|
|
|
|
|
%cmp = icmp sge i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-13 17:43:48 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_imax_sge_imm_i32:
|
|
|
|
|
; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9
|
|
|
|
|
define void @s_test_imax_sge_imm_i32(i32 addrspace(1)* %out, i32 %a) nounwind {
|
|
|
|
|
%cmp = icmp sge i32 %a, 9
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 9
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-19 02:39:48 +01:00
|
|
|
; FUNC-LABEL: {{^}}v_test_imax_sge_i8:
|
|
|
|
|
; SI: buffer_load_sbyte
|
|
|
|
|
; SI: buffer_load_sbyte
|
|
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
define void @v_test_imax_sge_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %aptr, i8 addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
|
|
|
%gep0 = getelementptr i8, i8 addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr i8, i8 addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr i8, i8 addrspace(1)* %out, i32 %tid
|
|
|
|
|
%a = load i8, i8 addrspace(1)* %gep0, align 1
|
|
|
|
|
%b = load i8, i8 addrspace(1)* %gep1, align 1
|
|
|
|
|
%cmp = icmp sge i8 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i8 %a, i8 %b
|
|
|
|
|
store i8 %val, i8 addrspace(1)* %outgep, align 1
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-13 17:43:48 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_imax_sgt_imm_i32:
|
|
|
|
|
; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9
|
|
|
|
|
define void @s_test_imax_sgt_imm_i32(i32 addrspace(1)* %out, i32 %a) nounwind {
|
|
|
|
|
%cmp = icmp sgt i32 %a, 9
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 9
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_imax_sgt_imm_v2i32:
|
|
|
|
|
; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9
|
|
|
|
|
; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9
|
|
|
|
|
define void @s_test_imax_sgt_imm_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %a) nounwind {
|
|
|
|
|
%cmp = icmp sgt <2 x i32> %a, <i32 9, i32 9>
|
|
|
|
|
%val = select <2 x i1> %cmp, <2 x i32> %a, <2 x i32> <i32 9, i32 9>
|
|
|
|
|
store <2 x i32> %val, <2 x i32> addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2014-11-14 19:30:06 +01:00
|
|
|
; FUNC-LABEL: @v_test_imax_sgt_i32
|
|
|
|
|
; SI: v_max_i32_e32
|
|
|
|
|
define void @v_test_imax_sgt_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = 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
2015-02-27 20:29:02 +01:00
|
|
|
%gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
|
2015-02-27 22:17:42 +01:00
|
|
|
%a = load i32, i32 addrspace(1)* %gep0, align 4
|
|
|
|
|
%b = load i32, i32 addrspace(1)* %gep1, align 4
|
2014-11-14 19:30:06 +01:00
|
|
|
%cmp = icmp sgt i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %outgep, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; FUNC-LABEL: @s_test_imax_sgt_i32
|
|
|
|
|
; SI: s_max_i32
|
|
|
|
|
define void @s_test_imax_sgt_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
|
|
|
|
|
%cmp = icmp sgt i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; FUNC-LABEL: @v_test_umax_uge_i32
|
|
|
|
|
; SI: v_max_u32_e32
|
|
|
|
|
define void @v_test_umax_uge_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = 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
2015-02-27 20:29:02 +01:00
|
|
|
%gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
|
2015-02-27 22:17:42 +01:00
|
|
|
%a = load i32, i32 addrspace(1)* %gep0, align 4
|
|
|
|
|
%b = load i32, i32 addrspace(1)* %gep1, align 4
|
2014-11-14 19:30:06 +01:00
|
|
|
%cmp = icmp uge i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %outgep, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; FUNC-LABEL: @s_test_umax_uge_i32
|
|
|
|
|
; SI: s_max_u32
|
|
|
|
|
define void @s_test_umax_uge_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
|
|
|
|
|
%cmp = icmp uge i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_umax_uge_v3i32:
|
|
|
|
|
; SI: s_max_u32
|
|
|
|
|
; SI: s_max_u32
|
|
|
|
|
; SI: s_max_u32
|
|
|
|
|
; SI-NOT: s_max_u32
|
|
|
|
|
; SI: s_endpgm
|
|
|
|
|
define void @s_test_umax_uge_v3i32(<3 x i32> addrspace(1)* %out, <3 x i32> %a, <3 x i32> %b) nounwind {
|
|
|
|
|
%cmp = icmp uge <3 x i32> %a, %b
|
|
|
|
|
%val = select <3 x i1> %cmp, <3 x i32> %a, <3 x i32> %b
|
|
|
|
|
store <3 x i32> %val, <3 x i32> addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-19 02:39:48 +01:00
|
|
|
; FUNC-LABEL: {{^}}v_test_umax_uge_i8:
|
|
|
|
|
; SI: buffer_load_ubyte
|
|
|
|
|
; SI: buffer_load_ubyte
|
|
|
|
|
; SI: v_max_u32_e32
|
|
|
|
|
define void @v_test_umax_uge_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %aptr, i8 addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
|
|
|
%gep0 = getelementptr i8, i8 addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr i8, i8 addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr i8, i8 addrspace(1)* %out, i32 %tid
|
|
|
|
|
%a = load i8, i8 addrspace(1)* %gep0, align 1
|
|
|
|
|
%b = load i8, i8 addrspace(1)* %gep1, align 1
|
|
|
|
|
%cmp = icmp uge i8 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i8 %a, i8 %b
|
|
|
|
|
store i8 %val, i8 addrspace(1)* %outgep, align 1
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2014-11-14 19:30:06 +01:00
|
|
|
; FUNC-LABEL: @v_test_umax_ugt_i32
|
|
|
|
|
; SI: v_max_u32_e32
|
|
|
|
|
define void @v_test_umax_ugt_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind {
|
|
|
|
|
%tid = 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
2015-02-27 20:29:02 +01:00
|
|
|
%gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
|
|
|
|
|
%gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid
|
|
|
|
|
%outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
|
2015-02-27 22:17:42 +01:00
|
|
|
%a = load i32, i32 addrspace(1)* %gep0, align 4
|
|
|
|
|
%b = load i32, i32 addrspace(1)* %gep1, align 4
|
2014-11-14 19:30:06 +01:00
|
|
|
%cmp = icmp ugt i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %outgep, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_umax_ugt_i32:
|
2014-11-14 19:30:06 +01:00
|
|
|
; SI: s_max_u32
|
|
|
|
|
define void @s_test_umax_ugt_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
|
|
|
|
|
%cmp = icmp ugt i32 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i32 %a, i32 %b
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2015-06-09 02:52:41 +02:00
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_umax_ugt_imm_v2i32:
|
|
|
|
|
; SI: s_max_u32 {{s[0-9]+}}, {{s[0-9]+}}, 15
|
|
|
|
|
; SI: s_max_u32 {{s[0-9]+}}, {{s[0-9]+}}, 23
|
|
|
|
|
define void @s_test_umax_ugt_imm_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %a) nounwind {
|
|
|
|
|
%cmp = icmp ugt <2 x i32> %a, <i32 15, i32 23>
|
|
|
|
|
%val = select <2 x i1> %cmp, <2 x i32> %a, <2 x i32> <i32 15, i32 23>
|
|
|
|
|
store <2 x i32> %val, <2 x i32> addrspace(1)* %out, align 4
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-06-09 02:52:41 +02:00
|
|
|
; Make sure redundant and removed
|
|
|
|
|
; FUNC-LABEL: {{^}}simplify_demanded_bits_test_umax_ugt_i16:
|
|
|
|
|
; SI-DAG: s_load_dword [[A:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, 0xb
|
|
|
|
|
; SI-DAG: s_load_dword [[B:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, 0xc
|
2015-12-12 00:16:47 +01:00
|
|
|
; SI: s_max_u32 [[MAX:s[0-9]+]], [[A]], [[B]]
|
|
|
|
|
; SI-NEXT: v_mov_b32_e32 [[VMAX:v[0-9]+]], [[MAX]]
|
|
|
|
|
; SI-NEXT: buffer_store_dword [[VMAX]]
|
2015-06-09 02:52:41 +02:00
|
|
|
define void @simplify_demanded_bits_test_umax_ugt_i16(i32 addrspace(1)* %out, i16 zeroext %a, i16 zeroext %b) nounwind {
|
|
|
|
|
%a.ext = zext i16 %a to i32
|
|
|
|
|
%b.ext = zext i16 %b to i32
|
|
|
|
|
%cmp = icmp ugt i32 %a.ext, %b.ext
|
|
|
|
|
%val = select i1 %cmp, i32 %a.ext, i32 %b.ext
|
|
|
|
|
%mask = and i32 %val, 65535
|
|
|
|
|
store i32 %mask, i32 addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Make sure redundant sign_extend_inreg removed.
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}simplify_demanded_bits_test_max_slt_i16:
|
2015-06-09 02:52:41 +02:00
|
|
|
; SI-DAG: s_load_dword [[A:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, 0xb
|
|
|
|
|
; SI-DAG: s_load_dword [[B:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, 0xc
|
2015-12-12 00:16:47 +01:00
|
|
|
; SI: s_max_i32 [[MAX:s[0-9]+]], [[A]], [[B]]
|
|
|
|
|
; SI-NEXT: v_mov_b32_e32 [[VMAX:v[0-9]+]], [[MAX]]
|
|
|
|
|
; SI-NEXT: buffer_store_dword [[VMAX]]
|
|
|
|
|
define void @simplify_demanded_bits_test_max_slt_i16(i32 addrspace(1)* %out, i16 signext %a, i16 signext %b) nounwind {
|
2015-06-09 02:52:41 +02:00
|
|
|
%a.ext = sext i16 %a to i32
|
|
|
|
|
%b.ext = sext i16 %b to i32
|
|
|
|
|
%cmp = icmp sgt i32 %a.ext, %b.ext
|
|
|
|
|
%val = select i1 %cmp, i32 %a.ext, i32 %b.ext
|
|
|
|
|
%shl = shl i32 %val, 16
|
|
|
|
|
%sextinreg = ashr i32 %shl, 16
|
|
|
|
|
store i32 %sextinreg, i32 addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-12-12 00:16:47 +01:00
|
|
|
; FUNC-LABEL: {{^}}s_test_imax_sge_i16:
|
2015-12-19 02:39:48 +01:00
|
|
|
; SI: s_load_dword
|
|
|
|
|
; SI: s_load_dword
|
|
|
|
|
; SI: s_sext_i32_i16
|
|
|
|
|
; SI: s_sext_i32_i16
|
2015-12-12 00:16:47 +01:00
|
|
|
; SI: s_max_i32
|
|
|
|
|
define void @s_test_imax_sge_i16(i16 addrspace(1)* %out, i16 %a, i16 %b) nounwind {
|
2015-06-09 02:52:41 +02:00
|
|
|
%cmp = icmp sge i16 %a, %b
|
|
|
|
|
%val = select i1 %cmp, i16 %a, i16 %b
|
|
|
|
|
store i16 %val, i16 addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
