2019-11-18 19:18:07 +08:00
|
|
|
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
|
2014-11-22 06:06:37 +08:00
|
|
|
|
|
|
|
|
; CHECK-LABEL: {{^}}fold_sgpr:
|
2015-08-29 15:16:50 +08:00
|
|
|
; CHECK: v_add_i32_e32 v{{[0-9]+}}, vcc, s
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @fold_sgpr(i32 addrspace(1)* %out, i32 %fold) #1 {
|
2014-11-22 06:06:37 +08:00
|
|
|
entry:
|
|
|
|
|
%tmp0 = icmp ne i32 %fold, 0
|
|
|
|
|
br i1 %tmp0, label %if, label %endif
|
|
|
|
|
|
|
|
|
|
if:
|
2016-02-11 14:02:01 +08:00
|
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x()
|
2014-11-22 06:06:37 +08:00
|
|
|
%offset = add i32 %fold, %id
|
[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
|
|
|
%tmp1 = getelementptr i32, i32 addrspace(1)* %out, i32 %offset
|
2014-11-22 06:06:37 +08:00
|
|
|
store i32 0, i32 addrspace(1)* %tmp1
|
|
|
|
|
br label %endif
|
|
|
|
|
|
|
|
|
|
endif:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: {{^}}fold_imm:
|
2015-03-28 04:41:42 +08:00
|
|
|
; CHECK: v_or_b32_e32 v{{[0-9]+}}, 5
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @fold_imm(i32 addrspace(1)* %out, i32 %cmp) #1 {
|
2014-11-22 06:06:37 +08:00
|
|
|
entry:
|
|
|
|
|
%fold = add i32 3, 2
|
|
|
|
|
%tmp0 = icmp ne i32 %cmp, 0
|
|
|
|
|
br i1 %tmp0, label %if, label %endif
|
|
|
|
|
|
|
|
|
|
if:
|
2016-02-11 14:02:01 +08:00
|
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x()
|
2014-11-22 06:06:37 +08:00
|
|
|
%val = or i32 %id, %fold
|
|
|
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
|
|
|
br label %endif
|
|
|
|
|
|
|
|
|
|
endif:
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-01-08 03:56:17 +08:00
|
|
|
; CHECK-LABEL: {{^}}fold_64bit_constant_add:
|
|
|
|
|
; CHECK-NOT: s_mov_b64
|
|
|
|
|
; FIXME: It would be better if we could use v_add here and drop the extra
|
|
|
|
|
; v_mov_b32 instructions.
|
|
|
|
|
; CHECK-DAG: s_add_u32 [[LO:s[0-9]+]], s{{[0-9]+}}, 1
|
|
|
|
|
; CHECK-DAG: s_addc_u32 [[HI:s[0-9]+]], s{{[0-9]+}}, 0
|
|
|
|
|
; CHECK-DAG: v_mov_b32_e32 v[[VLO:[0-9]+]], [[LO]]
|
|
|
|
|
; CHECK-DAG: v_mov_b32_e32 v[[VHI:[0-9]+]], [[HI]]
|
|
|
|
|
; CHECK: buffer_store_dwordx2 v{{\[}}[[VLO]]:[[VHI]]{{\]}},
|
|
|
|
|
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @fold_64bit_constant_add(i64 addrspace(1)* %out, i32 %cmp, i64 %val) #1 {
|
2015-01-08 03:56:17 +08:00
|
|
|
entry:
|
|
|
|
|
%tmp0 = add i64 %val, 1
|
|
|
|
|
store i64 %tmp0, i64 addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
2015-01-08 06:18:27 +08:00
|
|
|
; Inline constants should always be folded.
|
|
|
|
|
|
|
|
|
|
; CHECK-LABEL: {{^}}vector_inline:
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, 5, v{{[0-9]+}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, 5, v{{[0-9]+}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, 5, v{{[0-9]+}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, 5, v{{[0-9]+}}
|
|
|
|
|
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @vector_inline(<4 x i32> addrspace(1)* %out) #1 {
|
2015-01-08 06:18:27 +08:00
|
|
|
entry:
|
2016-02-11 14:02:01 +08:00
|
|
|
%tmp0 = call i32 @llvm.amdgcn.workitem.id.x()
|
2015-01-08 06:18:27 +08:00
|
|
|
%tmp1 = add i32 %tmp0, 1
|
|
|
|
|
%tmp2 = add i32 %tmp0, 2
|
|
|
|
|
%tmp3 = add i32 %tmp0, 3
|
|
|
|
|
%vec0 = insertelement <4 x i32> undef, i32 %tmp0, i32 0
|
|
|
|
|
%vec1 = insertelement <4 x i32> %vec0, i32 %tmp1, i32 1
|
|
|
|
|
%vec2 = insertelement <4 x i32> %vec1, i32 %tmp2, i32 2
|
|
|
|
|
%vec3 = insertelement <4 x i32> %vec2, i32 %tmp3, i32 3
|
|
|
|
|
%tmp4 = xor <4 x i32> <i32 5, i32 5, i32 5, i32 5>, %vec3
|
|
|
|
|
store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
; Immediates with one use should be folded
|
|
|
|
|
; CHECK-LABEL: {{^}}imm_one_use:
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, 0x64, v{{[0-9]+}}
|
|
|
|
|
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @imm_one_use(i32 addrspace(1)* %out) #1 {
|
2015-01-08 06:18:27 +08:00
|
|
|
entry:
|
2016-02-11 14:02:01 +08:00
|
|
|
%tmp0 = call i32 @llvm.amdgcn.workitem.id.x()
|
2015-01-08 06:18:27 +08:00
|
|
|
%tmp1 = xor i32 %tmp0, 100
|
|
|
|
|
store i32 %tmp1, i32 addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2015-01-08 23:08:17 +08:00
|
|
|
; CHECK-LABEL: {{^}}vector_imm:
|
|
|
|
|
; CHECK: s_movk_i32 [[IMM:s[0-9]+]], 0x64
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]}}, [[IMM]], v{{[0-9]}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]}}, [[IMM]], v{{[0-9]}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]}}, [[IMM]], v{{[0-9]}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]}}, [[IMM]], v{{[0-9]}}
|
|
|
|
|
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @vector_imm(<4 x i32> addrspace(1)* %out) #1 {
|
2015-01-08 23:08:17 +08:00
|
|
|
entry:
|
2016-02-11 14:02:01 +08:00
|
|
|
%tmp0 = call i32 @llvm.amdgcn.workitem.id.x()
|
2015-01-08 23:08:17 +08:00
|
|
|
%tmp1 = add i32 %tmp0, 1
|
|
|
|
|
%tmp2 = add i32 %tmp0, 2
|
|
|
|
|
%tmp3 = add i32 %tmp0, 3
|
|
|
|
|
%vec0 = insertelement <4 x i32> undef, i32 %tmp0, i32 0
|
|
|
|
|
%vec1 = insertelement <4 x i32> %vec0, i32 %tmp1, i32 1
|
|
|
|
|
%vec2 = insertelement <4 x i32> %vec1, i32 %tmp2, i32 2
|
|
|
|
|
%vec3 = insertelement <4 x i32> %vec2, i32 %tmp3, i32 3
|
|
|
|
|
%tmp4 = xor <4 x i32> <i32 100, i32 100, i32 100, i32 100>, %vec3
|
|
|
|
|
store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %out
|
|
|
|
|
ret void
|
|
|
|
|
}
|
2015-01-08 06:18:27 +08:00
|
|
|
|
2016-08-16 00:18:36 +08:00
|
|
|
; A subregister use operand should not be tied.
|
|
|
|
|
; CHECK-LABEL: {{^}}no_fold_tied_subregister:
|
|
|
|
|
; CHECK: buffer_load_dwordx2 v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]{{\]}}
|
|
|
|
|
; CHECK: v_mac_f32_e32 v[[LO]], 0x41200000, v[[HI]]
|
|
|
|
|
; CHECK: buffer_store_dword v[[LO]]
|
2019-11-18 19:18:07 +08:00
|
|
|
define amdgpu_kernel void @no_fold_tied_subregister() #1 {
|
2016-08-16 00:18:36 +08:00
|
|
|
%tmp1 = load volatile <2 x float>, <2 x float> addrspace(1)* undef
|
|
|
|
|
%tmp2 = extractelement <2 x float> %tmp1, i32 0
|
|
|
|
|
%tmp3 = extractelement <2 x float> %tmp1, i32 1
|
|
|
|
|
%tmp4 = fmul float %tmp3, 10.0
|
|
|
|
|
%tmp5 = fadd float %tmp4, %tmp2
|
|
|
|
|
store volatile float %tmp5, float addrspace(1)* undef
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
[AMDGPU] Skip additional folding on the same operand.
Reviewers: rampitec, arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69355
2019-10-24 03:19:06 +08:00
|
|
|
; There should be exact one folding on the same operand.
|
|
|
|
|
; CHECK-LABEL: {{^}}no_extra_fold_on_same_opnd
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, 0, v{{[0-9]+}}
|
|
|
|
|
; CHECK: v_xor_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
|
2019-11-18 19:18:07 +08:00
|
|
|
define void @no_extra_fold_on_same_opnd() #1 {
|
[AMDGPU] Skip additional folding on the same operand.
Reviewers: rampitec, arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69355
2019-10-24 03:19:06 +08:00
|
|
|
entry:
|
|
|
|
|
%s0 = load i32, i32 addrspace(5)* undef, align 4
|
|
|
|
|
%s0.i64= zext i32 %s0 to i64
|
|
|
|
|
br label %for.body.i.i
|
|
|
|
|
|
|
|
|
|
for.body.i.i:
|
|
|
|
|
%s1 = load i32, i32 addrspace(1)* undef, align 8
|
|
|
|
|
%s1.i64 = sext i32 %s1 to i64
|
|
|
|
|
%xor = xor i64 %s1.i64, %s0.i64
|
|
|
|
|
%flag = icmp ult i64 %xor, 8
|
|
|
|
|
br i1 %flag, label %if.then, label %if.else
|
|
|
|
|
|
|
|
|
|
if.then:
|
|
|
|
|
unreachable
|
|
|
|
|
|
|
|
|
|
if.else:
|
|
|
|
|
unreachable
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-11 14:02:01 +08:00
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
|
|
|
|
|
|
|
|
attributes #0 = { nounwind readnone }
|
2019-11-18 19:18:07 +08:00
|
|
|
attributes #1 = { nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" }
|