The semantics of tail predication loops means that the value of LR as an instruction is executed determines the predicate. In other words: mov r3, #3 DLSTP lr, r3 // Start tail predication, lr==3 VADD.s32 q0, q1, q2 // Lanes 0,1 and 2 are updated in q0. mov lr, #1 VADD.s32 q0, q1, q2 // Only first lane is updated. This means that the value of lr cannot be spilled and re-used in tail predication regions without potentially altering the behaviour of the program. More lanes than required could be stored, for example, and in the case of a gather those lanes might not have been setup, leading to alignment exceptions. This patch adds a new lr predicate operand to MVE instructions in order to keep a reference to the lr that they use as a tail predicate. It will usually hold the zeroreg meaning not predicated, being set to the LR phi value in the MVETPAndVPTOptimisationsPass. This will prevent it from being spilled anywhere that it needs to be used. A lot of tests needed updating. Differential Revision: https://reviews.llvm.org/D107638
185 lines
6.4 KiB
YAML
185 lines
6.4 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -o - %s -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -run-pass=stack-protector -run-pass=prologepilog | FileCheck %s
|
|
---
|
|
name: func0
|
|
tracksRegLiveness: true
|
|
stack:
|
|
- { id: 0, name: '', type: default, offset: 0, size: 16, alignment: 4,
|
|
stack-id: default, callee-saved-register: '', callee-saved-restored: true,
|
|
local-offset: -16, debug-info-variable: '', debug-info-expression: '',
|
|
debug-info-location: '' }
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: func0
|
|
; CHECK: liveins: $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r11, $lr
|
|
; CHECK: $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $r7, killed $r8, killed $r9, killed $r10, killed $r11, killed $lr
|
|
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 36
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r11, -8
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r10, -12
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r9, -16
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r8, -20
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -24
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r6, -28
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r5, -32
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r4, -36
|
|
; CHECK: $sp = frame-setup tSUBspi $sp, 5, 14 /* CC::al */, $noreg
|
|
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 56
|
|
; CHECK: $r0 = IMPLICIT_DEF
|
|
; CHECK: $r1 = IMPLICIT_DEF
|
|
; CHECK: $r2 = IMPLICIT_DEF
|
|
; CHECK: $r3 = IMPLICIT_DEF
|
|
; CHECK: $r4 = IMPLICIT_DEF
|
|
; CHECK: $r5 = IMPLICIT_DEF
|
|
; CHECK: $r6 = IMPLICIT_DEF
|
|
; CHECK: $r7 = IMPLICIT_DEF
|
|
; CHECK: $r8 = IMPLICIT_DEF
|
|
; CHECK: $r9 = IMPLICIT_DEF
|
|
; CHECK: $r10 = IMPLICIT_DEF
|
|
; CHECK: $r11 = IMPLICIT_DEF
|
|
; CHECK: $r12 = IMPLICIT_DEF
|
|
; CHECK: $lr = IMPLICIT_DEF
|
|
; CHECK: t2STRi12 killed $r0, $sp, 0, 14 /* CC::al */, $noreg :: (store (s32) into %stack.1)
|
|
; CHECK: $r0 = tMOVr killed $sp, 14 /* CC::al */, $noreg
|
|
; CHECK: renamable $q2 = MVE_VLDRBU32 killed $r0, 16, 0, $noreg, $noreg :: (load (s32) from %stack.0 + 12)
|
|
; CHECK: $r0 = t2LDRi12 $sp, 0, 14 /* CC::al */, $noreg :: (load (s32) from %stack.1)
|
|
; CHECK: KILL $r0
|
|
; CHECK: KILL $r1
|
|
; CHECK: KILL $r2
|
|
; CHECK: KILL $r3
|
|
; CHECK: KILL $r4
|
|
; CHECK: KILL $r5
|
|
; CHECK: KILL $r6
|
|
; CHECK: KILL $r7
|
|
; CHECK: KILL $r8
|
|
; CHECK: KILL $r9
|
|
; CHECK: KILL $r10
|
|
; CHECK: KILL $r11
|
|
; CHECK: KILL $r12
|
|
; CHECK: KILL $lr
|
|
$r0 = IMPLICIT_DEF
|
|
$r1 = IMPLICIT_DEF
|
|
$r2 = IMPLICIT_DEF
|
|
$r3 = IMPLICIT_DEF
|
|
$r4 = IMPLICIT_DEF
|
|
$r5 = IMPLICIT_DEF
|
|
$r6 = IMPLICIT_DEF
|
|
$r7 = IMPLICIT_DEF
|
|
$r8 = IMPLICIT_DEF
|
|
$r9 = IMPLICIT_DEF
|
|
$r10 = IMPLICIT_DEF
|
|
$r11 = IMPLICIT_DEF
|
|
$r12 = IMPLICIT_DEF
|
|
$lr = IMPLICIT_DEF
|
|
|
|
renamable $q2 = MVE_VLDRBU32 %stack.0, 12, 0, $noreg, $noreg :: (load (s32) from %stack.0 + 12)
|
|
|
|
KILL $r0
|
|
KILL $r1
|
|
KILL $r2
|
|
KILL $r3
|
|
KILL $r4
|
|
KILL $r5
|
|
KILL $r6
|
|
KILL $r7
|
|
KILL $r8
|
|
KILL $r9
|
|
KILL $r10
|
|
KILL $r11
|
|
KILL $r12
|
|
KILL $lr
|
|
...
|
|
---
|
|
name: func1
|
|
tracksRegLiveness: true
|
|
stack:
|
|
- { id: 0, name: '', type: default, offset: 0, size: 16, alignment: 4,
|
|
stack-id: default, callee-saved-register: '', callee-saved-restored: true,
|
|
local-offset: -1200, debug-info-variable: '', debug-info-expression: '',
|
|
debug-info-location: '' }
|
|
- { id: 1, name: '', type: default, offset: 0, size: 1200, alignment: 4,
|
|
stack-id: default, callee-saved-register: '', callee-saved-restored: true,
|
|
local-offset: -1200, debug-info-variable: '', debug-info-expression: '',
|
|
debug-info-location: '' }
|
|
body: |
|
|
bb.0:
|
|
; CHECK-LABEL: name: func1
|
|
; CHECK: liveins: $r4, $r5, $r6, $r7, $r8, $r9, $r10, $r11, $lr
|
|
; CHECK: $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $r7, killed $r8, killed $r9, killed $r10, killed $r11, killed $lr
|
|
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 36
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r11, -8
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r10, -12
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r9, -16
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r8, -20
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -24
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r6, -28
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r5, -32
|
|
; CHECK: frame-setup CFI_INSTRUCTION offset $r4, -36
|
|
; CHECK: $sp = frame-setup t2SUBspImm12 killed $sp, 1220, 14 /* CC::al */, $noreg
|
|
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 1256
|
|
; CHECK: $r0 = IMPLICIT_DEF
|
|
; CHECK: $r1 = IMPLICIT_DEF
|
|
; CHECK: $r2 = IMPLICIT_DEF
|
|
; CHECK: $r3 = IMPLICIT_DEF
|
|
; CHECK: $r4 = IMPLICIT_DEF
|
|
; CHECK: $r5 = IMPLICIT_DEF
|
|
; CHECK: $r6 = IMPLICIT_DEF
|
|
; CHECK: $r7 = IMPLICIT_DEF
|
|
; CHECK: $r8 = IMPLICIT_DEF
|
|
; CHECK: $r9 = IMPLICIT_DEF
|
|
; CHECK: $r10 = IMPLICIT_DEF
|
|
; CHECK: $r11 = IMPLICIT_DEF
|
|
; CHECK: $r12 = IMPLICIT_DEF
|
|
; CHECK: $lr = IMPLICIT_DEF
|
|
; CHECK: t2STRi12 killed $r0, $sp, 0, 14 /* CC::al */, $noreg :: (store (s32) into %stack.2)
|
|
; CHECK: $r0 = t2ADDri killed $sp, 1152, 14 /* CC::al */, $noreg, $noreg
|
|
; CHECK: renamable $q2 = MVE_VLDRBU8 killed $r0, 52, 0, $noreg, $noreg :: (load (s32) from %stack.0)
|
|
; CHECK: $r0 = t2LDRi12 $sp, 0, 14 /* CC::al */, $noreg :: (load (s32) from %stack.2)
|
|
; CHECK: KILL $r0
|
|
; CHECK: KILL $r1
|
|
; CHECK: KILL $r2
|
|
; CHECK: KILL $r3
|
|
; CHECK: KILL $r4
|
|
; CHECK: KILL $r5
|
|
; CHECK: KILL $r6
|
|
; CHECK: KILL $r7
|
|
; CHECK: KILL $r8
|
|
; CHECK: KILL $r9
|
|
; CHECK: KILL $r10
|
|
; CHECK: KILL $r11
|
|
; CHECK: KILL $r12
|
|
; CHECK: KILL $lr
|
|
$r0 = IMPLICIT_DEF
|
|
$r1 = IMPLICIT_DEF
|
|
$r2 = IMPLICIT_DEF
|
|
$r3 = IMPLICIT_DEF
|
|
$r4 = IMPLICIT_DEF
|
|
$r5 = IMPLICIT_DEF
|
|
$r6 = IMPLICIT_DEF
|
|
$r7 = IMPLICIT_DEF
|
|
$r8 = IMPLICIT_DEF
|
|
$r9 = IMPLICIT_DEF
|
|
$r10 = IMPLICIT_DEF
|
|
$r11 = IMPLICIT_DEF
|
|
$r12 = IMPLICIT_DEF
|
|
$lr = IMPLICIT_DEF
|
|
|
|
renamable $q2 = MVE_VLDRBU8 %stack.0, 0, 0, $noreg, $noreg :: (load (s32) from %stack.0)
|
|
|
|
KILL $r0
|
|
KILL $r1
|
|
KILL $r2
|
|
KILL $r3
|
|
KILL $r4
|
|
KILL $r5
|
|
KILL $r6
|
|
KILL $r7
|
|
KILL $r8
|
|
KILL $r9
|
|
KILL $r10
|
|
KILL $r11
|
|
KILL $r12
|
|
KILL $lr
|
|
...
|