b2ac9681a7
This changes the definition of t2DoLoopStart from
t2DoLoopStart rGPR
to
GPRlr = t2DoLoopStart rGPR
This will hopefully mean that low overhead loops are more tied together,
and we can more reliably generate loops without reverting or being at
the whims of the register allocator.
This is a fairly simple change in itself, but leads to a number of other
required alterations.
- The hardware loop pass, if UsePhi is set, now generates loops of the
form:
%start = llvm.start.loop.iterations(%N)
loop:
%p = phi [%start], [%dec]
%dec = llvm.loop.decrement.reg(%p, 1)
%c = icmp ne %dec, 0
br %c, loop, exit
- For this a new llvm.start.loop.iterations intrinsic was added, identical
to llvm.set.loop.iterations but produces a value as seen above, gluing
the loop together more through def-use chains.
- This new instrinsic conceptually produces the same output as input,
which is taught to SCEV so that the checks in MVETailPredication are not
affected.
- Some minor changes are needed to the ARMLowOverheadLoop pass, but it has
been left mostly as before. We should now more reliably be able to tell
that the t2DoLoopStart is correct without having to prove it, but
t2WhileLoopStart and tail-predicated loops will remain the same.
- And all the tests have been updated. There are a lot of them!
This patch on it's own might cause more trouble that it helps, with more
tail-predicated loops being reverted, but some additional patches can
hopefully improve upon that to get to something that is better overall.
Differential Revision: https://reviews.llvm.org/D89881
128 lines
3.9 KiB
YAML
128 lines
3.9 KiB
YAML
# RUN: llc -mtriple=thumbv8.1m.main %s -run-pass=arm-low-overhead-loops --verify-machineinstrs -o - | FileCheck %s
|
|
|
|
# CHECK: while.body:
|
|
# CHECK-NOT: t2DLS
|
|
# CHECK-NOT: t2LEUpdate
|
|
|
|
--- |
|
|
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 i32 @mov_between_dec_end(i32 %n) #0 {
|
|
entry:
|
|
%cmp6 = icmp eq i32 %n, 0
|
|
br i1 %cmp6, label %while.end, label %while.body.preheader
|
|
|
|
while.body.preheader: ; preds = %entry
|
|
%start = call i32 @llvm.start.loop.iterations.i32(i32 %n)
|
|
br label %while.body
|
|
|
|
while.body: ; preds = %while.body, %while.body.preheader
|
|
%0 = phi i32 [ %start, %while.body.preheader ], [ %1, %while.body ]
|
|
%1 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %0, i32 1)
|
|
%add = add i32 %1, 2
|
|
%2 = icmp ne i32 %1, 0
|
|
br i1 %2, label %while.body, label %while.end
|
|
|
|
while.end: ; preds = %while.body, %entry
|
|
%res.0.lcssa = phi i32 [ 0, %entry ], [ %add, %while.body ]
|
|
ret i32 %res.0.lcssa
|
|
}
|
|
|
|
; Function Attrs: noduplicate nounwind
|
|
declare i32 @llvm.start.loop.iterations.i32(i32) #1
|
|
|
|
; Function Attrs: noduplicate nounwind
|
|
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #1
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.stackprotector(i8*, i8**) #2
|
|
|
|
attributes #0 = { "target-features"="+mve.fp" }
|
|
attributes #1 = { noduplicate nounwind }
|
|
attributes #2 = { nounwind }
|
|
|
|
...
|
|
---
|
|
name: mov_between_dec_end
|
|
alignment: 2
|
|
exposesReturnsTwice: false
|
|
legalized: false
|
|
regBankSelected: false
|
|
selected: false
|
|
failedISel: false
|
|
tracksRegLiveness: true
|
|
hasWinCFI: false
|
|
registers: []
|
|
liveins:
|
|
- { reg: '$r0', virtual-reg: '' }
|
|
frameInfo:
|
|
isFrameAddressTaken: false
|
|
isReturnAddressTaken: false
|
|
hasStackMap: false
|
|
hasPatchPoint: false
|
|
stackSize: 8
|
|
offsetAdjustment: 0
|
|
maxAlignment: 4
|
|
adjustsStack: false
|
|
hasCalls: false
|
|
stackProtector: ''
|
|
maxCallFrameSize: 0
|
|
cvBytesOfCalleeSavedRegisters: 0
|
|
hasOpaqueSPAdjustment: false
|
|
hasVAStart: false
|
|
hasMustTailInVarArgFunc: false
|
|
localFrameSize: 0
|
|
savePoint: ''
|
|
restorePoint: ''
|
|
fixedStack: []
|
|
stack:
|
|
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
|
|
stack-id: default, callee-saved-register: '$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: |
|
|
bb.0.entry:
|
|
successors: %bb.4(0x30000000), %bb.1(0x50000000)
|
|
liveins: $r0, $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
|
|
tCBZ $r0, %bb.4
|
|
|
|
bb.1.while.body.preheader:
|
|
successors: %bb.2(0x80000000)
|
|
liveins: $r0
|
|
|
|
$lr = tMOVr $r0, 14, $noreg
|
|
$lr = t2DoLoopStart killed $r0
|
|
|
|
bb.2.while.body:
|
|
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
|
|
liveins: $lr
|
|
|
|
$r4 = tMOVr $lr, 14, $noreg
|
|
renamable $lr = t2LoopDec killed renamable $lr, 1
|
|
renamable $r0 = t2ADDri renamable $lr, 2, 14, $noreg, $noreg
|
|
$lr = tMOVr $r4, 14, $noreg
|
|
t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
|
|
tB %bb.3, 14, $noreg
|
|
|
|
bb.3.while.end:
|
|
liveins: $r0
|
|
|
|
tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0
|
|
|
|
bb.4:
|
|
renamable $r0, dead $cpsr = tMOVi8 0, 14, $noreg
|
|
tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0
|
|
|
|
...
|