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/propagate-attributes-clone.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

143 lines
4.9 KiB
LLVM
Raw Normal View History

[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -O1 < %s | FileCheck -check-prefixes=OPT,OPT-EXT %s
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -O1 --amdgpu-internalize-symbols < %s | FileCheck -check-prefixes=OPT,OPT-INT %s
[test] Fix tests when run on windows after SVN r369426. NFC. When running tests on windows, invoking "llc -march=<arch>" will implicitly use windows as the target os, making these tests misbehave after this change. Fix the issue by using more specific -mtriple values instead of plain -march in these tests. This should hopefully fix buildbot failures like http://lab.llvm.org:8011/builders/clang-x64-windows-msvc/builds/9816. llvm-svn: 369443
2019-08-21 04:58:02 +08:00
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefix=LLC %s
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; OPT: declare void @foo4() local_unnamed_addr #0
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; OPT: define internal fastcc void @0() unnamed_addr #1
; OPT-EXT: define void @foo3() local_unnamed_addr #1
; OPT-INT: define internal fastcc void @foo3.2() unnamed_addr #1
; OPT-EXT: define void @foo2() local_unnamed_addr #1
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-INT: define internal fastcc void @foo2.3() unnamed_addr #1
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; OPT-EXT: define void @foo1() local_unnamed_addr #1
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-EXT: tail call void @foo4()
; OPT-EXT: tail call void @foo3()
; OPT-EXT: tail call void @foo2()
; OPT-EXT: tail call void @foo2()
; OPT-EXT: tail call void @foo1()
; OPT-EXT: tail call fastcc void @0()
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; OPT-INT: define internal fastcc void @foo1.1() unnamed_addr #1
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-INT: tail call void @foo4()
; OPT-INT: tail call fastcc void @foo3.2()
; OPT-INT: tail call fastcc void @foo2.3()
; OPT-INT: tail call fastcc void @foo2.3()
; OPT-INT: tail call fastcc void @foo1.1()
; OPT-INT: tail call fastcc void @0()
; OPT: ret void
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; OPT: define amdgpu_kernel void @kernel1() local_unnamed_addr #2
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-EXT: tail call fastcc void @foo1.1()
; OPT-INT: tail call fastcc void @foo1()
; OPT: ret void
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; OPT: define amdgpu_kernel void @kernel2() local_unnamed_addr #3
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-EXT: tail call void @foo2()
; OPT-INT: tail call fastcc void @foo2.3()
; OPT: ret void
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; OPT: define amdgpu_kernel void @kernel3() local_unnamed_addr #3
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-EXT: tail call void @foo1()
; OPT-INT: tail call fastcc void @foo1.1()
; OPT: ret void
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; OPT-EXT: define internal fastcc void @foo1.1() unnamed_addr #4
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-EXT: tail call void @foo4()
; OPT-EXT: tail call fastcc void @foo3.2()
; OPT-EXT: tail call fastcc void @foo2.3()
; OPT-EXT: tail call fastcc void @foo2.3()
; OPT-EXT: tail call fastcc void @foo1.1()
; OPT-EXT: tail call fastcc void @1()
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; OPT-INT: define internal fastcc void @foo1() unnamed_addr #4
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-INT: tail call void @foo4()
; OPT-INT: tail call fastcc void @foo3()
; OPT-INT: tail call fastcc void @foo2()
; OPT-INT: tail call fastcc void @foo2()
; OPT-INT: tail call fastcc void @foo1()
; OPT-INT: tail call fastcc void @1()
; OPT: ret void
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; OPT: define internal fastcc void @1() unnamed_addr #4
; OPT-EXT: define internal fastcc void @foo3.2() unnamed_addr #4
; OPT-INT: define internal fastcc void @foo3() unnamed_addr #4
[AMDGPU] Fixed function traversal in attribute propagation AMDGPUPropagateAttributes pass was skipping some of the functions when cloning. Functions were added to root set and then skipped on the next interation because they are already in the root set, while were meant to be processed with different features. Differential Revision: https://reviews.llvm.org/D76815
2020-03-26 08:34:49 +08:00
; OPT-EXT: define internal fastcc void @foo2.3() unnamed_addr #4
; OPT-INT: define internal fastcc void @foo2() unnamed_addr #4
[AMDGPU] Propagate amdgpu-waves-per-eu to callees Differential Revision: https://reviews.llvm.org/D76868
2020-03-26 03:57:44 +08:00
; OPT: attributes #0 = { {{.*}} "amdgpu-waves-per-eu"="1,1" "target-features"="+wavefrontsize64" }
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; OPT: attributes #1 = { {{.*}} "target-features"="{{.*}},-wavefrontsize16,-wavefrontsize32,+wavefrontsize64{{.*}}" }
[AMDGPU] Propagate amdgpu-waves-per-eu to callees Differential Revision: https://reviews.llvm.org/D76868
2020-03-26 03:57:44 +08:00
; OPT: attributes #2 = { {{.*}} "amdgpu-waves-per-eu"="2,4" "target-features"="+wavefrontsize32" }
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; OPT: attributes #3 = { {{.*}} "target-features"="+wavefrontsize64" }
[AMDGPU] Propagate amdgpu-waves-per-eu to callees Differential Revision: https://reviews.llvm.org/D76868
2020-03-26 03:57:44 +08:00
; OPT: attributes #4 = { {{.*}} "amdgpu-waves-per-eu"="2,4" "target-features"="{{.*}},-wavefrontsize16,+wavefrontsize32,-wavefrontsize64{{.*}}" }
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; LLC: foo3:
; LLC: sample asm
; LLC: foo2:
; LLC: sample asm
; LLC: foo1:
; LLC: foo4@gotpcrel32@lo+4
; LLC: foo4@gotpcrel32@hi+4
; LLC: foo3@gotpcrel32@lo+4
; LLC: foo3@gotpcrel32@hi+4
; LLC: foo2@gotpcrel32@lo+4
; LLC: foo2@gotpcrel32@hi+4
; LLC: foo1@gotpcrel32@lo+4
; LLC: foo1@gotpcrel32@hi+4
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
; LLC: __unnamed_1@gotpcrel32@lo+4
; LLC: __unnamed_1@gotpcrel32@hi+4
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
; LLC: kernel1:
; LLC: foo1@gotpcrel32@lo+4
; LLC: foo1@gotpcrel32@hi+4
; LLC: kernel2:
; LLC: foo2@gotpcrel32@lo+4
; LLC: foo2@gotpcrel32@hi+4
; LLC: kernel3:
; LLC: foo1@gotpcrel32@lo+4
; LLC: foo1@gotpcrel32@hi+4
declare void @foo4() #1
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
define void @0() #1 {
entry:
call void asm sideeffect "; sample asm", ""()
ret void
}
[AMDGPU] Propagate amdgpu-waves-per-eu to callees Differential Revision: https://reviews.llvm.org/D76868
2020-03-26 03:57:44 +08:00
define void @foo3() #4 {
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
entry:
call void asm sideeffect "; sample asm", ""()
ret void
}
define void @foo2() #1 {
entry:
call void asm sideeffect "; sample asm", ""()
ret void
}
define void @foo1() #1 {
entry:
tail call void @foo4()
tail call void @foo3()
tail call void @foo2()
tail call void @foo2()
tail call void @foo1()
[AMDGPU] Preserve original symbol during attribute propagation AMDGPUPropagateAttributes can swap names while cloning a function. Only do it if original symbol was not externally visible. Differential Revision: https://reviews.llvm.org/D76789
2020-03-26 02:06:34 +08:00
tail call void @0()
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
ret void
}
define amdgpu_kernel void @kernel1() #0 {
entry:
tail call void @foo1()
ret void
}
define amdgpu_kernel void @kernel2() #2 {
entry:
tail call void @foo2()
ret void
}
define amdgpu_kernel void @kernel3() #3 {
entry:
tail call void @foo1()
ret void
}
[AMDGPU] Propagate amdgpu-waves-per-eu to callees Differential Revision: https://reviews.llvm.org/D76868
2020-03-26 03:57:44 +08:00
attributes #0 = { nounwind "target-features"="+wavefrontsize32" "amdgpu-waves-per-eu"="2,4" }
attributes #1 = { noinline nounwind "target-features"="+wavefrontsize64" "amdgpu-waves-per-eu"="1,1" }
[AMDGPU] Pass to propagate ABI attributes from kernels to the functions The pass works in two modes: Mode 1: Just set attributes starting from kernels. This can work at the very beginning of opt and llc pipeline, but cannot clone functions because it must be a function pass. Mode 2: Actually clone functions for new attributes. This can only work after all function passes in the opt pipeline because it has to be a module pass. Differential Revision: https://reviews.llvm.org/D63208 llvm-svn: 363586
2019-06-18 01:47:28 +08:00
attributes #2 = { nounwind "target-features"="+wavefrontsize64" }
attributes #3 = { nounwind "target-features"="+wavefrontsize64" }
[AMDGPU] Propagate amdgpu-waves-per-eu to callees Differential Revision: https://reviews.llvm.org/D76868
2020-03-26 03:57:44 +08:00
attributes #4 = { noinline nounwind "target-features"="+wavefrontsize64" "amdgpu-waves-per-eu"="2,4" }