caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
3eed57e7ef7da5eda765ccc19fd26fb8dfcd8d41
clang-p2996/llvm/test/CodeGen/Thumb2/LowOverheadLoops/while.mir
David Green fad70c3068 [ARM] Improve WLS lowering 
Recently we improved the lowering of low overhead loops and tail
predicated loops, but concentrated first on the DLS do style loops. This
extends those improvements over to the WLS while loops, improving the
chance of lowering them successfully. To do this the lowering has to
change a little as the instructions are terminators that produce a value
- something that needs to be treated carefully.

Lowering starts at the Hardware Loop pass, inserting a new
llvm.test.start.loop.iterations that produces both an i1 to control the
loop entry and an i32 similar to the llvm.start.loop.iterations
intrinsic added for do loops. This feeds into the loop phi, properly
gluing the values together:

  %wls = call { i32, i1 } @llvm.test.start.loop.iterations.i32(i32 %div)
  %wls0 = extractvalue { i32, i1 } %wls, 0
  %wls1 = extractvalue { i32, i1 } %wls, 1
  br i1 %wls1, label %loop.ph, label %loop.exit
...
loop:
  %lsr.iv = phi i32 [ %wls0, %loop.ph ], [ %iv.next, %loop ]
  ..
  %iv.next = call i32 @llvm.loop.decrement.reg.i32(i32 %lsr.iv, i32 1)
  %cmp = icmp ne i32 %iv.next, 0
  br i1 %cmp, label %loop, label %loop.exit

The llvm.test.start.loop.iterations need to be lowered through ISel
lowering as a pair of WLS and WLSSETUP nodes, which each get converted
to t2WhileLoopSetup and t2WhileLoopStart Pseudos. This helps prevent
t2WhileLoopStart from being a terminator that produces a value,
something difficult to control at that stage in the pipeline. Instead
the t2WhileLoopSetup produces the value of LR (essentially acting as a
lr = subs rn, 0), t2WhileLoopStart consumes that lr value (the Bcc).

These are then converted into a single t2WhileLoopStartLR at the same
point as t2DoLoopStartTP and t2LoopEndDec. Otherwise we revert the loop
to prevent them from progressing further in the pipeline. The
t2WhileLoopStartLR is a single instruction that takes a GPR and produces
LR, similar to the WLS instruction.

  %1:gprlr = t2WhileLoopStartLR %0:rgpr, %bb.3
  t2B %bb.1
...
bb.2.loop:
  %2:gprlr = PHI %1:gprlr, %bb.1, %3:gprlr, %bb.2
  ...
  %3:gprlr = t2LoopEndDec %2:gprlr, %bb.2
  t2B %bb.3

The t2WhileLoopStartLR can then be treated similar to the other low
overhead loop pseudos, eventually being lowered to a WLS providing the
branches are within range.

Differential Revision: https://reviews.llvm.org/D97729
2021-03-11 17:56:19 +00:00

147 lines
5.9 KiB
YAML
Raw Blame History

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv8.1m.main -mattr=+lob %s -run-pass=arm-low-overhead-loops --verify-machineinstrs -o - | FileCheck %s
# TODO: Remove the lr = tMOVr which actually makes the WLS def dead!
--- |
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main"
define dso_local arm_aapcscc void @copy(i16* nocapture %a, i16* nocapture readonly %b, i32 %N) {
entry:
%0 = call i1 @llvm.test.set.loop.iterations.i32(i32 %N)
br i1 %0, label %while.body.preheader, label %while.end
while.body.preheader: ; preds = %entry
%scevgep = getelementptr i16, i16* %a, i32 -1
%scevgep3 = getelementptr i16, i16* %b, i32 -1
br label %while.body
while.body: ; preds = %while.body, %while.body.preheader
%lsr.iv4 = phi i16* [ %scevgep3, %while.body.preheader ], [ %scevgep5, %while.body ]
%lsr.iv = phi i16* [ %scevgep, %while.body.preheader ], [ %scevgep1, %while.body ]
%1 = phi i32 [ %3, %while.body ], [ %N, %while.body.preheader ]
%scevgep7 = getelementptr i16, i16* %lsr.iv, i32 1
%scevgep4 = getelementptr i16, i16* %lsr.iv4, i32 1
%2 = load i16, i16* %scevgep4, align 2
store i16 %2, i16* %scevgep7, align 2
%3 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %1, i32 1)
%4 = icmp ne i32 %3, 0
%scevgep1 = getelementptr i16, i16* %lsr.iv, i32 1
%scevgep5 = getelementptr i16, i16* %lsr.iv4, i32 1
br i1 %4, label %while.body, label %while.end
while.end: ; preds = %while.body, %entry
ret void
}
declare i1 @llvm.test.set.loop.iterations.i32(i32) #0
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #0
attributes #0 = { noduplicate nounwind }
attributes #1 = { nounwind }
...
---
name: copy
alignment: 2
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
failedISel: false
tracksRegLiveness: true
hasWinCFI: false
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
adjustsStack: false
hasCalls: false
stackProtector: ''
maxCallFrameSize: 0
cvBytesOfCalleeSavedRegisters: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
localFrameSize: 0
savePoint: ''
restorePoint: ''
fixedStack: []
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: copy
; CHECK: bb.0.entry:
; CHECK: successors: %bb.1(0x40000000), %bb.3(0x40000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r7
; CHECK: frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8
; CHECK: dead $lr = t2WLS $r2, %bb.3
; CHECK: bb.1.while.body.preheader:
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r1, $r2
; CHECK: renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 2, 14 /* CC::al */, $noreg
; CHECK: renamable $r0, dead $cpsr = tSUBi8 killed renamable $r0, 2, 14 /* CC::al */, $noreg
; CHECK: $lr = tMOVr killed $r2, 14 /* CC::al */, $noreg
; CHECK: bb.2.while.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $lr, $r0, $r1
; CHECK: renamable $r2, renamable $r1 = t2LDRH_PRE killed renamable $r1, 2, 14 /* CC::al */, $noreg :: (load 2 from %ir.scevgep4)
; CHECK: early-clobber renamable $r0 = t2STRH_PRE killed renamable $r2, killed renamable $r0, 2, 14 /* CC::al */, $noreg :: (store 2 into %ir.scevgep7)
; CHECK: $lr = t2LEUpdate killed renamable $lr, %bb.2
; CHECK: bb.3.while.end:
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc
bb.0.entry:
successors: %bb.1(0x40000000), %bb.3(0x40000000)
liveins: $r0, $r1, $r2, $r7, $lr
frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r7, -8
$lr = t2WhileLoopStartLR $r2, %bb.3, implicit-def dead $cpsr
tB %bb.1, 14, $noreg
bb.1.while.body.preheader:
successors: %bb.2(0x80000000)
liveins: $r0, $r1, $r2
renamable $r1, dead $cpsr = tSUBi8 killed renamable $r1, 2, 14, $noreg
renamable $r0, dead $cpsr = tSUBi8 killed renamable $r0, 2, 14, $noreg
$lr = tMOVr killed $r2, 14, $noreg
bb.2.while.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $lr, $r0, $r1
renamable $r2, renamable $r1 = t2LDRH_PRE killed renamable $r1, 2, 14, $noreg :: (load 2 from %ir.scevgep4)
early-clobber renamable $r0 = t2STRH_PRE killed renamable $r2, killed renamable $r0, 2, 14, $noreg :: (store 2 into %ir.scevgep7)
renamable $lr = t2LoopDec killed renamable $lr, 1
t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14, $noreg
bb.3.while.end:
tPOP_RET 14, $noreg, def $r7, def $pc
...
Reference in New Issue View Git Blame Copy Permalink