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/llvm.amdgcn.class.ll

500 lines
20 KiB
LLVM
Raw Normal View History

R600: Move DataLayout to AMDGPUTargetMachine This is a follow up to r227113. It is now required to use the amdgcn target for SI and newer GPUs. llvm-svn: 227316
2015-01-29 00:04:26 +08:00
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
declare i1 @llvm.amdgcn.class.f32(float, i32) #1
declare i1 @llvm.amdgcn.class.f64(double, i32) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
declare i32 @llvm.r600.read.tidig.x() #1
declare float @llvm.fabs.f32(float) #1
declare double @llvm.fabs.f64(double) #1
; SI-LABEL: {{^}}test_class_f32:
; SI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
; SI: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f32_e32 vcc, [[SA]], [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_f32(i32 addrspace(1)* %out, float %a, i32 %b) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_fabs_f32:
; SI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
; SI: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f32_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], |[[SA]]|, [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_fabs_f32(i32 addrspace(1)* %out, float %a, i32 %b) #0 {
%a.fabs = call float @llvm.fabs.f32(float %a) #1
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a.fabs, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_fneg_f32:
; SI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
; SI: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f32_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], -[[SA]], [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_fneg_f32(i32 addrspace(1)* %out, float %a, i32 %b) #0 {
%a.fneg = fsub float -0.0, %a
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a.fneg, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_fneg_fabs_f32:
; SI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xc
; SI: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f32_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], -|[[SA]]|, [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_fneg_fabs_f32(i32 addrspace(1)* %out, float %a, i32 %b) #0 {
%a.fabs = call float @llvm.fabs.f32(float %a) #1
%a.fneg.fabs = fsub float -0.0, %a.fabs
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a.fneg.fabs, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_1_f32:
; SI: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI: v_cmp_class_f32_e64 [[COND:s\[[0-9]+:[0-9]+\]]], [[SA]], 1{{$}}
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[COND]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_1_f32(i32 addrspace(1)* %out, float %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 1) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_64_f32:
; SI: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI: v_cmp_class_f32_e64 [[COND:s\[[0-9]+:[0-9]+\]]], [[SA]], 64{{$}}
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[COND]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_64_f32(i32 addrspace(1)* %out, float %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 64) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; Set all 10 bits of mask
; SI-LABEL: {{^}}test_class_full_mask_f32:
; SI: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI: v_mov_b32_e32 [[MASK:v[0-9]+]], 0x3ff{{$}}
; SI: v_cmp_class_f32_e32 vcc, [[SA]], [[MASK]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_full_mask_f32(i32 addrspace(1)* %out, float %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 1023) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_9bit_mask_f32:
; SI: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI: v_mov_b32_e32 [[MASK:v[0-9]+]], 0x1ff{{$}}
; SI: v_cmp_class_f32_e32 vcc, [[SA]], [[MASK]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_9bit_mask_f32(i32 addrspace(1)* %out, float %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 511) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}v_test_class_full_mask_f32:
; SI-DAG: buffer_load_dword [[VA:v[0-9]+]]
; SI-DAG: v_mov_b32_e32 [[MASK:v[0-9]+]], 0x1ff{{$}}
; SI: v_cmp_class_f32_e32 vcc, [[VA]], [[MASK]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @v_test_class_full_mask_f32(i32 addrspace(1)* %out, float addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 511) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %gep.out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_inline_imm_constant_dynamic_mask_f32:
; SI-DAG: buffer_load_dword [[VB:v[0-9]+]]
; SI: v_cmp_class_f32_e32 vcc, 1.0, [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_inline_imm_constant_dynamic_mask_f32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%b = load i32, i32 addrspace(1)* %gep.in
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float 1.0, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %gep.out, align 4
ret void
}
; FIXME: Why isn't this using a literal constant operand?
; SI-LABEL: {{^}}test_class_lit_constant_dynamic_mask_f32:
; SI-DAG: buffer_load_dword [[VB:v[0-9]+]]
; SI-DAG: v_mov_b32_e32 [[VK:v[0-9]+]], 0x44800000
; SI: v_cmp_class_f32_e32 vcc, [[VK]], [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_lit_constant_dynamic_mask_f32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%b = load i32, i32 addrspace(1)* %gep.in
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float 1024.0, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %gep.out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_f64:
; SI-DAG: s_load_dwordx2 [[SA:s\[[0-9]+:[0-9]+\]]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xd
; SI-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f64_e32 vcc, [[SA]], [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_f64(i32 addrspace(1)* %out, double %a, i32 %b) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_fabs_f64:
; SI-DAG: s_load_dwordx2 [[SA:s\[[0-9]+:[0-9]+\]]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xd
; SI-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f64_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], |[[SA]]|, [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_fabs_f64(i32 addrspace(1)* %out, double %a, i32 %b) #0 {
%a.fabs = call double @llvm.fabs.f64(double %a) #1
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a.fabs, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_fneg_f64:
; SI-DAG: s_load_dwordx2 [[SA:s\[[0-9]+:[0-9]+\]]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xd
; SI-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f64_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], -[[SA]], [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_fneg_f64(i32 addrspace(1)* %out, double %a, i32 %b) #0 {
%a.fneg = fsub double -0.0, %a
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a.fneg, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_fneg_fabs_f64:
; SI-DAG: s_load_dwordx2 [[SA:s\[[0-9]+:[0-9]+\]]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xd
; SI-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
; SI: v_cmp_class_f64_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], -|[[SA]]|, [[VB]]
; SI-NEXT: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, [[CMP]]
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_fneg_fabs_f64(i32 addrspace(1)* %out, double %a, i32 %b) #0 {
%a.fabs = call double @llvm.fabs.f64(double %a) #1
%a.fneg.fabs = fsub double -0.0, %a.fabs
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a.fneg.fabs, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_1_f64:
; SI: v_cmp_class_f64_e64 {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 1{{$}}
; SI: s_endpgm
define void @test_class_1_f64(i32 addrspace(1)* %out, double %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a, i32 1) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_64_f64:
; SI: v_cmp_class_f64_e64 {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 64{{$}}
; SI: s_endpgm
define void @test_class_64_f64(i32 addrspace(1)* %out, double %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a, i32 64) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; Set all 9 bits of mask
; SI-LABEL: {{^}}test_class_full_mask_f64:
; SI: s_load_dwordx2 [[SA:s\[[0-9]+:[0-9]+\]]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
; SI: v_mov_b32_e32 [[MASK:v[0-9]+]], 0x1ff{{$}}
; SI: v_cmp_class_f64_e32 vcc, [[SA]], [[MASK]]
AMDGPU: Improve accuracy of instruction rates for VOPC These were all using the default 32-bit VALU write class, but the i64/f64 compares are half rate. I'm not sure this is really correct, because they are still using the write to VALU write class, even though they really write to the SALU. llvm-svn: 248582
2015-09-26 00:58:25 +08:00
; SI-NOT: vcc
; SI: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
; SI-NEXT: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_full_mask_f64(i32 addrspace(1)* %out, double %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a, i32 511) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}v_test_class_full_mask_f64:
; SI-DAG: buffer_load_dwordx2 [[VA:v\[[0-9]+:[0-9]+\]]]
; SI-DAG: v_mov_b32_e32 [[MASK:v[0-9]+]], 0x1ff{{$}}
; SI: v_cmp_class_f64_e32 vcc, [[VA]], [[MASK]]
AMDGPU: Improve accuracy of instruction rates for VOPC These were all using the default 32-bit VALU write class, but the i64/f64 compares are half rate. I'm not sure this is really correct, because they are still using the write to VALU write class, even though they really write to the SALU. llvm-svn: 248582
2015-09-26 00:58:25 +08:00
; SI-NOT: vcc
; SI: v_cndmask_b32_e64 [[RESULT:v[0-9]+]], 0, -1, vcc
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @v_test_class_full_mask_f64(i32 addrspace(1)* %out, double addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr double, double addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%a = load double, double addrspace(1)* %in
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a, i32 511) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %gep.out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_inline_imm_constant_dynamic_mask_f64:
; XSI: v_cmp_class_f64_e32 vcc, 1.0,
; SI: v_cmp_class_f64_e32 vcc,
; SI: s_endpgm
define void @test_class_inline_imm_constant_dynamic_mask_f64(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%b = load i32, i32 addrspace(1)* %gep.in
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double 1.0, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %gep.out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_lit_constant_dynamic_mask_f64:
; SI: v_cmp_class_f64_e32 vcc, s{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}
; SI: s_endpgm
define void @test_class_lit_constant_dynamic_mask_f64(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%b = load i32, i32 addrspace(1)* %gep.in
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double 1024.0, i32 %b) #1
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %gep.out, align 4
ret void
}
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
; SI-LABEL: {{^}}test_fold_or_class_f32_0:
; SI-NOT: v_cmp_class
; SI: v_cmp_class_f32_e64 {{s\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, 3{{$}}
; SI-NOT: v_cmp_class
; SI: s_endpgm
define void @test_fold_or_class_f32_0(i32 addrspace(1)* %out, float addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%class0 = call i1 @llvm.amdgcn.class.f32(float %a, i32 1) #1
%class1 = call i1 @llvm.amdgcn.class.f32(float %a, i32 3) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%or = or i1 %class0, %class1
%sext = sext i1 %or to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_fold_or3_class_f32_0:
; SI-NOT: v_cmp_class
; SI: v_cmp_class_f32_e64 s{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, 7{{$}}
; SI-NOT: v_cmp_class
; SI: s_endpgm
define void @test_fold_or3_class_f32_0(i32 addrspace(1)* %out, float addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%class0 = call i1 @llvm.amdgcn.class.f32(float %a, i32 1) #1
%class1 = call i1 @llvm.amdgcn.class.f32(float %a, i32 2) #1
%class2 = call i1 @llvm.amdgcn.class.f32(float %a, i32 4) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%or.0 = or i1 %class0, %class1
%or.1 = or i1 %or.0, %class2
%sext = sext i1 %or.1 to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_fold_or_all_tests_class_f32_0:
; SI-NOT: v_cmp_class
; SI: v_mov_b32_e32 [[MASK:v[0-9]+]], 0x3ff{{$}}
; SI: v_cmp_class_f32_e32 vcc, v{{[0-9]+}}, [[MASK]]{{$}}
; SI-NOT: v_cmp_class
; SI: s_endpgm
define void @test_fold_or_all_tests_class_f32_0(i32 addrspace(1)* %out, float addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%class0 = call i1 @llvm.amdgcn.class.f32(float %a, i32 1) #1
%class1 = call i1 @llvm.amdgcn.class.f32(float %a, i32 2) #1
%class2 = call i1 @llvm.amdgcn.class.f32(float %a, i32 4) #1
%class3 = call i1 @llvm.amdgcn.class.f32(float %a, i32 8) #1
%class4 = call i1 @llvm.amdgcn.class.f32(float %a, i32 16) #1
%class5 = call i1 @llvm.amdgcn.class.f32(float %a, i32 32) #1
%class6 = call i1 @llvm.amdgcn.class.f32(float %a, i32 64) #1
%class7 = call i1 @llvm.amdgcn.class.f32(float %a, i32 128) #1
%class8 = call i1 @llvm.amdgcn.class.f32(float %a, i32 256) #1
%class9 = call i1 @llvm.amdgcn.class.f32(float %a, i32 512) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%or.0 = or i1 %class0, %class1
%or.1 = or i1 %or.0, %class2
%or.2 = or i1 %or.1, %class3
%or.3 = or i1 %or.2, %class4
%or.4 = or i1 %or.3, %class5
%or.5 = or i1 %or.4, %class6
%or.6 = or i1 %or.5, %class7
%or.7 = or i1 %or.6, %class8
%or.8 = or i1 %or.7, %class9
%sext = sext i1 %or.8 to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_fold_or_class_f32_1:
; SI-NOT: v_cmp_class
; SI: v_cmp_class_f32_e64 {{s\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, 12{{$}}
; SI-NOT: v_cmp_class
; SI: s_endpgm
define void @test_fold_or_class_f32_1(i32 addrspace(1)* %out, float addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%class0 = call i1 @llvm.amdgcn.class.f32(float %a, i32 4) #1
%class1 = call i1 @llvm.amdgcn.class.f32(float %a, i32 8) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%or = or i1 %class0, %class1
%sext = sext i1 %or to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_fold_or_class_f32_2:
; SI-NOT: v_cmp_class
; SI: v_cmp_class_f32_e64 {{s\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, 7{{$}}
; SI-NOT: v_cmp_class
; SI: s_endpgm
define void @test_fold_or_class_f32_2(i32 addrspace(1)* %out, float addrspace(1)* %in) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%class0 = call i1 @llvm.amdgcn.class.f32(float %a, i32 7) #1
%class1 = call i1 @llvm.amdgcn.class.f32(float %a, i32 7) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%or = or i1 %class0, %class1
%sext = sext i1 %or to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_no_fold_or_class_f32_0:
; SI-DAG: v_cmp_class_f32_e64 {{s\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, 4{{$}}
; SI-DAG: v_cmp_class_f32_e64 {{s\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}}, 8{{$}}
; SI: s_or_b64
; SI: s_endpgm
define void @test_no_fold_or_class_f32_0(i32 addrspace(1)* %out, float addrspace(1)* %in, float %b) #0 {
%tid = call i32 @llvm.r600.read.tidig.x() #1
[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
%gep.in = getelementptr float, float addrspace(1)* %in, i32 %tid
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
[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]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load float, float addrspace(1)* %gep.in
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%class0 = call i1 @llvm.amdgcn.class.f32(float %a, i32 4) #1
%class1 = call i1 @llvm.amdgcn.class.f32(float %b, i32 8) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%or = or i1 %class0, %class1
%sext = sext i1 %or to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_0_f32:
; SI-NOT: v_cmp_class
; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
R600/SI: Enable subreg liveness by default llvm-svn: 228228
2015-02-05 07:14:18 +08:00
; SI: buffer_store_dword [[RESULT]]
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
; SI: s_endpgm
define void @test_class_0_f32(i32 addrspace(1)* %out, float %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f32(float %a, i32 0) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: {{^}}test_class_0_f64:
; SI-NOT: v_cmp_class
; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
; SI: buffer_store_dword [[RESULT]]
; SI: s_endpgm
define void @test_class_0_f64(i32 addrspace(1)* %out, double %a) #0 {
AMDGPU: Rename intrinsics to use amdgcn prefix The intrinsic target prefix should match the target name as it appears in the triple. This is not yet complete, but gets most of the important ones. llvm.AMDGPU.* intrinsics used by mesa and libclc are still handled for compatability for now. llvm-svn: 258557
2016-01-23 05:30:34 +08:00
%result = call i1 @llvm.amdgcn.class.f64(double %a, i32 0) #1
R600/SI: Add basic DAG combines for fp_class llvm-svn: 225306
2015-01-07 07:00:39 +08:00
%sext = sext i1 %result to i32
store i32 %sext, i32 addrspace(1)* %out, align 4
ret void
}
R600/SI: Add class intrinsic llvm-svn: 225305
2015-01-07 07:00:37 +08:00
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }