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/detect-dead-lanes.mir

420 lines
12 KiB
Plaintext
Raw Normal View History

[MIR] Print on the given output instead of stderr. Currently the MIR framework prints all its outputs (errors and actual representation) on stderr. This patch fixes that by printing the regular output in the output specified with -o. Differential Revision: http://reviews.llvm.org/D22251 llvm-svn: 275314
2016-07-14 04:36:03 +08:00
# RUN: llc -march=amdgcn -run-pass detect-dead-lanes -o - %s | FileCheck %s
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
--- |
define void @test0() { ret void }
define void @test1() { ret void }
define void @test2() { ret void }
define void @test3() { ret void }
define void @test4() { ret void }
DetectDeadLanes: Increase precision when detecting undef inputs In case of COPY-like instruction we may be able to deduce that a certain input is unused, based on the used lanes of the register defined by the instruction. This even works accross otherwise incompatible copies (no need to have compatible lanemasks, completely unused operands are still completely unused). It even makes sense to redo the analysis in this case since we gained information for a case we previously stopped at because of the incompatible masks. llvm-svn: 268815
2016-05-07 06:43:50 +08:00
define void @test5() { ret void }
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
define void @loop0() { ret void }
define void @loop1() { ret void }
define void @loop2() { ret void }
...
---
# Combined use/def transfer check, the basics.
# CHECK-LABEL: name: test0
# CHECK: S_NOP 0, implicit-def %0
# CHECK: S_NOP 0, implicit-def %1
# CHECK: S_NOP 0, implicit-def dead %2
# CHECK: %3 = REG_SEQUENCE %0, {{[0-9]+}}, %1, {{[0-9]+}}, undef %2, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %3.sub0
# CHECK: S_NOP 0, implicit %3.sub1
# CHECK: S_NOP 0, implicit undef %3.sub2
# CHECK: %4 = COPY %3.sub0_sub1
# CHECK: %5 = COPY undef %3.sub2_sub3
# CHECK: S_NOP 0, implicit %4.sub0
# CHECK: S_NOP 0, implicit %4.sub1
# CHECK: S_NOP 0, implicit undef %5.sub0
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
name: test0
registers:
- { id: 0, class: sreg_32 }
- { id: 1, class: sreg_32 }
- { id: 2, class: sreg_32 }
- { id: 3, class: sreg_128 }
- { id: 4, class: sreg_64 }
- { id: 5, class: sreg_64 }
body: |
bb.0:
S_NOP 0, implicit-def %0
S_NOP 0, implicit-def %1
S_NOP 0, implicit-def %2
%3 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1, %2, %subreg.sub3
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %3.sub0
S_NOP 0, implicit %3.sub1
S_NOP 0, implicit %3.sub2
%4 = COPY %3.sub0_sub1
%5 = COPY %3.sub2_sub3
S_NOP 0, implicit %4.sub0
S_NOP 0, implicit %4.sub1
S_NOP 0, implicit %5.sub0
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
...
---
# Check defined lanes transfer; Includes checking for some special cases like
# undef operands or IMPLICIT_DEF definitions.
# CHECK-LABEL: name: test1
# CHECK: %0 = REG_SEQUENCE %sgpr0, {{[0-9]+}}, %sgpr0, {{[0-9]+}}
# CHECK: %1 = INSERT_SUBREG %0, %sgpr1, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: %2 = INSERT_SUBREG %0.sub2_sub3, %sgpr42, {{[0-9]+}}
# CHECK: S_NOP 0, implicit %1.sub0
# CHECK: S_NOP 0, implicit undef %1.sub1
# CHECK: S_NOP 0, implicit %1.sub2
# CHECK: S_NOP 0, implicit %1.sub3
# CHECK: S_NOP 0, implicit %2.sub0
# CHECK: S_NOP 0, implicit undef %2.sub1
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: %3 = IMPLICIT_DEF
# CHECK: %4 = INSERT_SUBREG %0, undef %3, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit undef %4.sub0
# CHECK: S_NOP 0, implicit undef %4.sub1
# CHECK: S_NOP 0, implicit %4.sub2
# CHECK: S_NOP 0, implicit undef %4.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: %5 = EXTRACT_SUBREG %0, {{[0-9]+}}
# CHECK: %6 = EXTRACT_SUBREG %5, {{[0-9]+}}
# CHECK: %7 = EXTRACT_SUBREG %5, {{[0-9]+}}
# CHECK: S_NOP 0, implicit %5
# CHECK: S_NOP 0, implicit %6
# CHECK: S_NOP 0, implicit undef %7
# CHECK: %8 = IMPLICIT_DEF
# CHECK: %9 = EXTRACT_SUBREG undef %8, {{[0-9]+}}
# CHECK: S_NOP 0, implicit undef %9
# CHECK: %10 = EXTRACT_SUBREG undef %0, {{[0-9]+}}
# CHECK: S_NOP 0, implicit undef %10
name: test1
registers:
- { id: 0, class: sreg_128 }
- { id: 1, class: sreg_128 }
- { id: 2, class: sreg_64 }
- { id: 3, class: sreg_32 }
- { id: 4, class: sreg_128 }
- { id: 5, class: sreg_64 }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32 }
- { id: 8, class: sreg_64 }
- { id: 9, class: sreg_32 }
- { id: 10, class: sreg_128 }
body: |
bb.0:
%0 = REG_SEQUENCE %sgpr0, %subreg.sub0, %sgpr0, %subreg.sub2
%1 = INSERT_SUBREG %0, %sgpr1, %subreg.sub3
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
%2 = INSERT_SUBREG %0.sub2_sub3, %sgpr42, %subreg.sub0
S_NOP 0, implicit %1.sub0
S_NOP 0, implicit %1.sub1
S_NOP 0, implicit %1.sub2
S_NOP 0, implicit %1.sub3
S_NOP 0, implicit %2.sub0
S_NOP 0, implicit %2.sub1
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
%3 = IMPLICIT_DEF
%4 = INSERT_SUBREG %0, %3, %subreg.sub0
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %4.sub0
S_NOP 0, implicit %4.sub1
S_NOP 0, implicit %4.sub2
S_NOP 0, implicit %4.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
%5 = EXTRACT_SUBREG %0, %subreg.sub0_sub1
%6 = EXTRACT_SUBREG %5, %subreg.sub0
%7 = EXTRACT_SUBREG %5, %subreg.sub1
S_NOP 0, implicit %5
S_NOP 0, implicit %6
S_NOP 0, implicit %7
%8 = IMPLICIT_DEF
%9 = EXTRACT_SUBREG %8, %subreg.sub1
S_NOP 0, implicit %9
%10 = EXTRACT_SUBREG undef %0, %subreg.sub2_sub3
S_NOP 0, implicit %10
...
---
# Check used lanes transfer; Includes checking for some special cases like
# undef operands.
# CHECK-LABEL: name: test2
# CHECK: S_NOP 0, implicit-def dead %0
# CHECK: S_NOP 0, implicit-def %1
# CHECK: S_NOP 0, implicit-def %2
# CHECK: %3 = REG_SEQUENCE undef %0, {{[0-9]+}}, %1, {{[0-9]+}}, %2, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %3.sub1
# CHECK: S_NOP 0, implicit %3.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: S_NOP 0, implicit-def %4
# CHECK: S_NOP 0, implicit-def dead %5
# CHECK: %6 = REG_SEQUENCE %4, {{[0-9]+}}, undef %5, {{[0-9]+}}
# CHECK: S_NOP 0, implicit %6
# CHECK: S_NOP 0, implicit-def dead %7
# CHECK: S_NOP 0, implicit-def %8
# CHECK: %9 = INSERT_SUBREG undef %7, %8, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %9.sub2
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: S_NOP 0, implicit-def %10
# CHECK: S_NOP 0, implicit-def dead %11
# CHECK: %12 = INSERT_SUBREG %10, undef %11, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %12.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: S_NOP 0, implicit-def %13
# CHECK: S_NOP 0, implicit-def dead %14
# CHECK: %15 = REG_SEQUENCE %13, {{[0-9]+}}, undef %14, {{[0-9]+}}
# CHECK: %16 = EXTRACT_SUBREG %15, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %16.sub1
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
name: test2
registers:
- { id: 0, class: sreg_32 }
- { id: 1, class: sreg_32 }
- { id: 2, class: sreg_64 }
- { id: 3, class: sreg_128 }
- { id: 4, class: sreg_32 }
- { id: 5, class: sreg_32 }
- { id: 6, class: sreg_64 }
- { id: 7, class: sreg_128 }
- { id: 8, class: sreg_64 }
- { id: 9, class: sreg_128 }
- { id: 10, class: sreg_128 }
- { id: 11, class: sreg_64 }
- { id: 12, class: sreg_128 }
- { id: 13, class: sreg_64 }
- { id: 14, class: sreg_64 }
- { id: 15, class: sreg_128 }
- { id: 16, class: sreg_64 }
body: |
bb.0:
S_NOP 0, implicit-def %0
S_NOP 0, implicit-def %1
S_NOP 0, implicit-def %2
%3 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1, %2, %subreg.sub2_sub3
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %3.sub1
S_NOP 0, implicit %3.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
S_NOP 0, implicit-def %4
S_NOP 0, implicit-def %5
%6 = REG_SEQUENCE %4, %subreg.sub0, undef %5, %subreg.sub1
S_NOP 0, implicit %6
S_NOP 0, implicit-def %7
S_NOP 0, implicit-def %8
%9 = INSERT_SUBREG %7, %8, %subreg.sub2_sub3
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %9.sub2
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
S_NOP 0, implicit-def %10
S_NOP 0, implicit-def %11
%12 = INSERT_SUBREG %10, %11, %subreg.sub0_sub1
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %12.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
S_NOP 0, implicit-def %13
S_NOP 0, implicit-def %14
%15 = REG_SEQUENCE %13, %subreg.sub0_sub1, %14, %subreg.sub2_sub3
%16 = EXTRACT_SUBREG %15, %subreg.sub0_sub1
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %16.sub1
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
...
---
# Check that copies to physregs use all lanes, copies from physregs define all
# lanes. So we should not get a dead/undef flag here.
# CHECK-LABEL: name: test3
# CHECK: S_NOP 0, implicit-def %0
# CHECK: %vcc = COPY %0
# CHECK: %1 = COPY %vcc
# CHECK: S_NOP 0, implicit %1
name: test3
tracksRegLiveness: true
registers:
- { id: 0, class: sreg_64 }
- { id: 1, class: sreg_64 }
body: |
bb.0:
S_NOP 0, implicit-def %0
%vcc = COPY %0
%1 = COPY %vcc
S_NOP 0, implicit %1
...
---
# Check that implicit-def/kill do not count as def/uses.
# CHECK-LABEL: name: test4
# CHECK: S_NOP 0, implicit-def dead %0
# CHECK: KILL undef %0
# CHECK: %1 = IMPLICIT_DEF
# CHECK: S_NOP 0, implicit undef %1
name: test4
tracksRegLiveness: true
registers:
- { id: 0, class: sreg_64 }
- { id: 1, class: sreg_64 }
body: |
bb.0:
S_NOP 0, implicit-def %0
KILL %0
%1 = IMPLICIT_DEF
S_NOP 0, implicit %1
...
---
DetectDeadLanes: Increase precision when detecting undef inputs In case of COPY-like instruction we may be able to deduce that a certain input is unused, based on the used lanes of the register defined by the instruction. This even works accross otherwise incompatible copies (no need to have compatible lanemasks, completely unused operands are still completely unused). It even makes sense to redo the analysis in this case since we gained information for a case we previously stopped at because of the incompatible masks. llvm-svn: 268815
2016-05-07 06:43:50 +08:00
# Check that unused inputs are marked as undef, even if the vreg itself is
# used.
# CHECK-LABEL: name: test5
# CHECK: S_NOP 0, implicit-def %0
# CHECK: %1 = REG_SEQUENCE undef %0, {{[0-9]+}}, %0, {{[0-9]+}}
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %1.sub1
DetectDeadLanes: Increase precision when detecting undef inputs In case of COPY-like instruction we may be able to deduce that a certain input is unused, based on the used lanes of the register defined by the instruction. This even works accross otherwise incompatible copies (no need to have compatible lanemasks, completely unused operands are still completely unused). It even makes sense to redo the analysis in this case since we gained information for a case we previously stopped at because of the incompatible masks. llvm-svn: 268815
2016-05-07 06:43:50 +08:00
name: test5
tracksRegLiveness: true
registers:
- { id: 0, class: sreg_32 }
- { id: 1, class: sreg_64 }
body: |
bb.0:
S_NOP 0, implicit-def %0
%1 = REG_SEQUENCE %0, %subreg.sub0, %0, %subreg.sub1
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %1.sub1
DetectDeadLanes: Increase precision when detecting undef inputs In case of COPY-like instruction we may be able to deduce that a certain input is unused, based on the used lanes of the register defined by the instruction. This even works accross otherwise incompatible copies (no need to have compatible lanemasks, completely unused operands are still completely unused). It even makes sense to redo the analysis in this case since we gained information for a case we previously stopped at because of the incompatible masks. llvm-svn: 268815
2016-05-07 06:43:50 +08:00
...
---
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# Check "optimistic" dataflow fixpoint in phi-loops.
# CHECK-LABEL: name: loop0
# CHECK: bb.0:
# CHECK: S_NOP 0, implicit-def %0
# CHECK: S_NOP 0, implicit-def dead %1
# CHECK: S_NOP 0, implicit-def dead %2
# CHECK: %3 = REG_SEQUENCE %0, {{[0-9]+}}, undef %1, {{[0-9]+}}, undef %2, {{[0-9]+}}
# CHECK: bb.1:
# CHECK: %4 = PHI %3, %bb.0, %5, %bb.1
# CHECK: bb.2:
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %4.sub0
# CHECK: S_NOP 0, implicit undef %4.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
name: loop0
tracksRegLiveness: true
registers:
- { id: 0, class: sreg_32 }
- { id: 1, class: sreg_32 }
- { id: 2, class: sreg_32 }
- { id: 3, class: sreg_128 }
- { id: 4, class: sreg_128 }
- { id: 5, class: sreg_128 }
body: |
bb.0:
successors: %bb.1
S_NOP 0, implicit-def %0
S_NOP 0, implicit-def %1
S_NOP 0, implicit-def %2
%3 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1, %2, %subreg.sub2
S_BRANCH %bb.1
bb.1:
successors: %bb.1, %bb.2
%4 = PHI %3, %bb.0, %5, %bb.1
; let's swiffle some lanes around for fun...
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
%5 = REG_SEQUENCE %4.sub0, %subreg.sub0, %4.sub2, %subreg.sub1, %4.sub1, %subreg.sub2, %4.sub3, %subreg.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
S_BRANCH %bb.2
bb.2:
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %4.sub0
S_NOP 0, implicit %4.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
...
---
# Check a loop that needs to be traversed multiple times to reach the fixpoint
# for the used lanes. The example reads sub3 lane at the end, however with each
# loop iteration we should get 1 more lane marked as we cycles the sublanes
# along. Sublanes sub0, sub1 and sub3 are rotate in the loop so only sub2
# should be dead.
# CHECK-LABEL: name: loop1
# CHECK: bb.0:
# CHECK: S_NOP 0, implicit-def %0
# CHECK: S_NOP 0, implicit-def %1
# CHECK: S_NOP 0, implicit-def dead %2
# CHECK: S_NOP 0, implicit-def %3
# CHECK: %4 = REG_SEQUENCE %0, {{[0-9]+}}, %1, {{[0-9]+}}, undef %2, {{[0-9]+}}, %3, {{[0-9]+}}
# CHECK: bb.1:
# CHECK: %5 = PHI %4, %bb.0, %6, %bb.1
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: %6 = REG_SEQUENCE %5.sub1, {{[0-9]+}}, %5.sub3, {{[0-9]+}}, undef %5.sub2, {{[0-9]+}}, %5.sub0, {{[0-9]+}}
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: bb.2:
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %6.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
name: loop1
tracksRegLiveness: true
registers:
- { id: 0, class: sreg_32 }
- { id: 1, class: sreg_32 }
- { id: 2, class: sreg_32 }
- { id: 3, class: sreg_32 }
- { id: 4, class: sreg_128 }
- { id: 5, class: sreg_128 }
- { id: 6, class: sreg_128 }
body: |
bb.0:
successors: %bb.1
S_NOP 0, implicit-def %0
S_NOP 0, implicit-def %1
S_NOP 0, implicit-def dead %2
S_NOP 0, implicit-def %3
%4 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1, %2, %subreg.sub2, %3, %subreg.sub3
S_BRANCH %bb.1
bb.1:
successors: %bb.1, %bb.2
%5 = PHI %4, %bb.0, %6, %bb.1
; rotate lanes, but skip sub2 lane...
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
%6 = REG_SEQUENCE %5.sub1, %subreg.sub0, %5.sub3, %subreg.sub1, %5.sub2, %subreg.sub2, %5.sub0, %subreg.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
S_BRANCH %bb.2
bb.2:
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %6.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
...
---
# Similar to loop1 test, but check for fixpoint of defined lanes.
# Lanes are rotate between sub0, sub2, sub3 so only sub1 should be dead/undef.
# CHECK-LABEL: name: loop2
# CHECK: bb.0:
# CHECK: S_NOP 0, implicit-def %0
# CHECK: %1 = REG_SEQUENCE %0, {{[0-9]+}}
# CHECK: bb.1:
# CHECK: %2 = PHI %1, %bb.0, %3, %bb.1
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: %3 = REG_SEQUENCE %2.sub3, {{[0-9]+}}, undef %2.sub1, {{[0-9]+}}, %2.sub0, {{[0-9]+}}, %2.sub2, {{[0-9]+}}
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
# CHECK: bb.2:
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
# CHECK: S_NOP 0, implicit %2.sub0
# CHECK: S_NOP 0, implicit undef %2.sub1
# CHECK: S_NOP 0, implicit %2.sub2
# CHECK: S_NOP 0, implicit %2.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
name: loop2
tracksRegLiveness: true
registers:
- { id: 0, class: sreg_32 }
- { id: 1, class: sreg_128 }
- { id: 2, class: sreg_128 }
- { id: 3, class: sreg_128 }
body: |
bb.0:
successors: %bb.1
S_NOP 0, implicit-def %0
%1 = REG_SEQUENCE %0, %subreg.sub0
S_BRANCH %bb.1
bb.1:
successors: %bb.1, %bb.2
%2 = PHI %1, %bb.0, %3, %bb.1
; rotate subreg lanes, skipping sub1
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
%3 = REG_SEQUENCE %2.sub3, %subreg.sub0, %2.sub1, %subreg.sub1, %2.sub0, %subreg.sub2, %2.sub2, %subreg.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
S_BRANCH %bb.2
bb.2:
MIRParser: Use dot instead of colon to mark subregisters Change the syntax to use `%0.sub8` to denote a subregister. This seems like a more natural fit to denote subregisters; I also plan to introduce a new ":classname" syntax in upcoming patches to denote the register class of a vreg. Note that this commit disallows plain identifiers to start with a '.' character. This shouldn't affect anything as external names/IR references are all prefixed with '$'/'%', plain identifiers are only used for instruction names, register mask names and subreg indexes. Differential Revision: https://reviews.llvm.org/D22390 llvm-svn: 276815
2016-07-27 05:49:34 +08:00
S_NOP 0, implicit %2.sub0
S_NOP 0, implicit undef %2.sub1
S_NOP 0, implicit %2.sub2
S_NOP 0, implicit %2.sub3
CodeGen: Add DetectDeadLanes pass. The DetectDeadLanes pass performs a dataflow analysis of used/defined subregister lanes across COPY instructions and instructions that will get lowered to copies. It detects dead definitions and uses reading undefined values which are obscured by COPY and subregister usage. These dead definitions cause trouble in the register coalescer which cannot deal with definitions suddenly becoming dead after coalescing COPY instructions. For now the pass only adds dead and undef flags to machine operands. It should be possible to extend it in the future to remove the dead instructions and redo the analysis for the affected virtual registers. Differential Revision: http://reviews.llvm.org/D18427 llvm-svn: 267851
2016-04-28 11:07:16 +08:00
...