ab393cee9d
If we know vlen is a multiple of 16, we don't need any alignment padding. I wrote the code so that it would generate the minimum amount of padding if the stack align was 32 or larger or if RVVBitsPerBlock was smaller than half the stack alignment.
202 lines
8.7 KiB
YAML
202 lines
8.7 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
# RUN: llc -mtriple riscv64 -mattr=+m,+v -run-pass=prologepilog \
|
|
# RUN: -riscv-v-vector-bits-min=512 -o - %s | FileCheck %s
|
|
#
|
|
# Stack layout of this program
|
|
# |--------------------------| -- <-- Incoming SP
|
|
# | a7 (Vaarg) |
|
|
# | ------------------------ | -- <-- New SP + vlenb + 72
|
|
# | a6 (Vaarg) |
|
|
# | ------------------------ | -- <-- New SP + vlenb + 64
|
|
# | ra (Callee-saved reg) |
|
|
# | ------------------------ | -- <-- New SP + vlenb + 56
|
|
# | s0 (Callee-saved reg) |
|
|
# | ------------------------ | -- <-- New SP + vlenb + 48
|
|
# | s1 (Callee-saved reg) |
|
|
# | ------------------------ | -- <-- New SP + vlenb + 40
|
|
# | 8 bytes of padding |
|
|
# | ------------------------ | -- <-- New SP + vlenb
|
|
# | v8 (RVV objects) |
|
|
# | ------------------------ | -- <-- New SP + 32
|
|
# | buf1 |
|
|
# |--------------------------| -- <-- New SP + 16
|
|
# | Stack ID 5 |
|
|
# |--------------------------| -- <-- New SP + 8
|
|
# | Stack ID 6 |
|
|
# |--------------------------| -- <-- New SP
|
|
|
|
--- |
|
|
source_filename = "wrong-stack-offset-for-rvv-object.ll"
|
|
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
|
|
target triple = "riscv64"
|
|
|
|
%struct = type { i32 }
|
|
|
|
define void @asm_fprintf(%struct %file, ptr %p, ptr %buf, ptr %arrayidx3, ptr %0, ptr %1, ...) #0 {
|
|
entry:
|
|
%buf1 = alloca [10 x i8], i32 0, align 8
|
|
%arrayidx32 = getelementptr inbounds [10 x i8], ptr %buf, i64 0, i64 1
|
|
br label %while.cond
|
|
|
|
while.cond: ; preds = %while.cond, %sw.bb, %entry
|
|
%incdec.ptr = getelementptr inbounds i8, ptr undef, i64 1
|
|
%2 = load i8, ptr null, align 1
|
|
%3 = zext i8 0 to i64
|
|
%cond = icmp eq i64 %3, 0
|
|
br i1 %cond, label %sw.bb, label %while.cond
|
|
|
|
sw.bb: ; preds = %while.cond
|
|
%4 = load i8, ptr null, align 1
|
|
store <2 x i8> zeroinitializer, ptr %0, align 1
|
|
%call = call i32 (ptr, ...) @fprintf(ptr %p)
|
|
br label %while.cond
|
|
}
|
|
|
|
declare i32 @fprintf(ptr, ...) #0
|
|
|
|
attributes #0 = { "target-features"="+m,+v" }
|
|
|
|
...
|
|
---
|
|
name: asm_fprintf
|
|
alignment: 4
|
|
exposesReturnsTwice: false
|
|
legalized: false
|
|
regBankSelected: false
|
|
selected: false
|
|
failedISel: false
|
|
tracksRegLiveness: true
|
|
hasWinCFI: false
|
|
failsVerification: false
|
|
tracksDebugUserValues: true
|
|
registers: []
|
|
liveins:
|
|
- { reg: '$x11', virtual-reg: '' }
|
|
- { reg: '$x14', virtual-reg: '' }
|
|
- { reg: '$x16', virtual-reg: '' }
|
|
- { reg: '$x17', virtual-reg: '' }
|
|
frameInfo:
|
|
isFrameAddressTaken: false
|
|
isReturnAddressTaken: false
|
|
hasStackMap: false
|
|
hasPatchPoint: false
|
|
stackSize: 0
|
|
offsetAdjustment: 0
|
|
maxAlignment: 8
|
|
adjustsStack: true
|
|
hasCalls: true
|
|
stackProtector: ''
|
|
maxCallFrameSize: 4294967295
|
|
cvBytesOfCalleeSavedRegisters: 0
|
|
hasOpaqueSPAdjustment: false
|
|
hasVAStart: false
|
|
hasMustTailInVarArgFunc: false
|
|
hasTailCall: false
|
|
localFrameSize: 0
|
|
savePoint: ''
|
|
restorePoint: ''
|
|
fixedStack:
|
|
- { id: 0, type: default, offset: -8, size: 8, alignment: 8, stack-id: default,
|
|
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
|
|
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
- { id: 1, type: default, offset: -16, size: 8, alignment: 16, stack-id: default,
|
|
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
|
|
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
- { id: 2, type: default, offset: -16, size: 8, alignment: 16, stack-id: default,
|
|
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
|
|
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
stack:
|
|
- { id: 0, name: buf1, type: default, offset: 0, size: 1, alignment: 8,
|
|
stack-id: default, callee-saved-register: '', callee-saved-restored: true,
|
|
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
- { id: 1, name: '', type: spill-slot, offset: 0, size: 8, alignment: 8,
|
|
stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
|
|
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
callSites: []
|
|
debugValueSubstitutions: []
|
|
constants: []
|
|
machineFunctionInfo:
|
|
varArgsFrameIndex: -1
|
|
varArgsSaveSize: 16
|
|
body: |
|
|
; CHECK-LABEL: name: asm_fprintf
|
|
; CHECK: bb.0.entry:
|
|
; CHECK-NEXT: successors: %bb.1(0x80000000)
|
|
; CHECK-NEXT: liveins: $x11, $x14, $x16, $x17, $x1, $x8, $x9
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: $x2 = frame-setup ADDI $x2, -80
|
|
; CHECK-NEXT: frame-setup CFI_INSTRUCTION def_cfa_offset 80
|
|
; CHECK-NEXT: SD killed $x1, $x2, 56 :: (store (s64) into %stack.2)
|
|
; CHECK-NEXT: SD killed $x8, $x2, 48 :: (store (s64) into %stack.3)
|
|
; CHECK-NEXT: SD killed $x9, $x2, 40 :: (store (s64) into %stack.4)
|
|
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $x1, -24
|
|
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $x8, -32
|
|
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $x9, -40
|
|
; CHECK-NEXT: $x10 = frame-setup PseudoReadVLENB
|
|
; CHECK-NEXT: $x2 = frame-setup SUB $x2, killed $x10
|
|
; CHECK-NEXT: frame-setup CFI_INSTRUCTION escape 0x0f, 0x0e, 0x72, 0x00, 0x11, 0xd0, 0x00, 0x22, 0x11, 0x01, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22
|
|
; CHECK-NEXT: renamable $x8 = COPY $x14
|
|
; CHECK-NEXT: renamable $x9 = COPY $x11
|
|
; CHECK-NEXT: $x10 = PseudoReadVLENB
|
|
; CHECK-NEXT: $x10 = ADD $x2, killed $x10
|
|
; CHECK-NEXT: SD killed renamable $x17, killed $x10, 72 :: (store (s64))
|
|
; CHECK-NEXT: $x10 = PseudoReadVLENB
|
|
; CHECK-NEXT: $x10 = ADD $x2, killed $x10
|
|
; CHECK-NEXT: SD killed renamable $x16, killed $x10, 64 :: (store (s64) into %fixed-stack.1, align 16)
|
|
; CHECK-NEXT: dead $x0 = PseudoVSETIVLI 2, 69 /* e8, mf8, ta, mu */, implicit-def $vl, implicit-def $vtype
|
|
; CHECK-NEXT: renamable $v8 = PseudoVMV_V_I_MF8 undef $v8, 0, 2, 3 /* e8 */, 0 /* tu, mu */, implicit $vl, implicit $vtype
|
|
; CHECK-NEXT: $x10 = ADDI $x2, 32
|
|
; CHECK-NEXT: VS1R_V killed renamable $v8, killed $x10 :: (store unknown-size into %stack.1, align 8)
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.1.while.cond:
|
|
; CHECK-NEXT: successors: %bb.2(0x30000000), %bb.1(0x50000000)
|
|
; CHECK-NEXT: liveins: $x8, $x9
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: BNE $x0, $x0, %bb.1
|
|
; CHECK-NEXT: PseudoBR %bb.2
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: bb.2.sw.bb:
|
|
; CHECK-NEXT: successors: %bb.1(0x80000000)
|
|
; CHECK-NEXT: liveins: $x8, $x9
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: dead $x0 = PseudoVSETIVLI 2, 69 /* e8, mf8, ta, mu */, implicit-def $vl, implicit-def $vtype
|
|
; CHECK-NEXT: $x10 = ADDI $x2, 32
|
|
; CHECK-NEXT: renamable $v8 = VL1RE8_V killed $x10 :: (load unknown-size from %stack.1, align 8)
|
|
; CHECK-NEXT: PseudoVSE8_V_MF8 killed renamable $v8, renamable $x8, 2, 3 /* e8 */, implicit $vl, implicit $vtype :: (store (s16) into %ir.0, align 1)
|
|
; CHECK-NEXT: $x10 = COPY renamable $x9
|
|
; CHECK-NEXT: PseudoCALL target-flags(riscv-call) @fprintf, csr_ilp32d_lp64d, implicit-def dead $x1, implicit killed $x10, implicit-def $x2, implicit-def dead $x10
|
|
; CHECK-NEXT: PseudoBR %bb.1
|
|
bb.0.entry:
|
|
successors: %bb.1(0x80000000)
|
|
liveins: $x11, $x14, $x16, $x17
|
|
|
|
renamable $x8 = COPY $x14
|
|
renamable $x9 = COPY $x11
|
|
SD killed renamable $x17, %fixed-stack.0, 0 :: (store (s64))
|
|
SD killed renamable $x16, %fixed-stack.1, 0 :: (store (s64) into %fixed-stack.1, align 16)
|
|
dead $x0 = PseudoVSETIVLI 2, 69, implicit-def $vl, implicit-def $vtype
|
|
renamable $v8 = PseudoVMV_V_I_MF8 undef $v8, 0, 2, 3, 0, implicit $vl, implicit $vtype
|
|
VS1R_V killed renamable $v8, %stack.1 :: (store unknown-size into %stack.1, align 8)
|
|
|
|
bb.1.while.cond:
|
|
successors: %bb.2(0x30000000), %bb.1(0x50000000)
|
|
liveins: $x8, $x9
|
|
|
|
BNE $x0, $x0, %bb.1
|
|
PseudoBR %bb.2
|
|
|
|
bb.2.sw.bb:
|
|
successors: %bb.1(0x80000000)
|
|
liveins: $x8, $x9
|
|
|
|
dead $x0 = PseudoVSETIVLI 2, 69, implicit-def $vl, implicit-def $vtype
|
|
renamable $v8 = VL1RE8_V %stack.1 :: (load unknown-size from %stack.1, align 8)
|
|
PseudoVSE8_V_MF8 killed renamable $v8, renamable $x8, 2, 3, implicit $vl, implicit $vtype :: (store (s16) into %ir.0, align 1)
|
|
ADJCALLSTACKDOWN 0, 0, implicit-def dead $x2, implicit $x2
|
|
$x10 = COPY renamable $x9
|
|
PseudoCALL target-flags(riscv-call) @fprintf, csr_ilp32d_lp64d, implicit-def dead $x1, implicit killed $x10, implicit-def $x2, implicit-def dead $x10
|
|
ADJCALLSTACKUP 0, 0, implicit-def dead $x2, implicit $x2
|
|
PseudoBR %bb.1
|
|
|
|
...
|