llvm-project/llvm/test/CodeGen/X86/peephole-recurrence.mir

233 lines
6.7 KiB
YAML

# RUN: llc -mtriple=x86_64-- -run-pass=peephole-opt -o - %s | FileCheck %s
--- |
define i32 @foo(i32 %a) {
bb0:
br label %bb1
bb1: ; preds = %bb7, %bb0
%vreg0 = phi i32 [ 0, %bb0 ], [ %vreg3, %bb7 ]
%cond0 = icmp eq i32 %a, 0
br i1 %cond0, label %bb4, label %bb3
bb3: ; preds = %bb1
br label %bb4
bb4: ; preds = %bb1, %bb3
%vreg5 = phi i32 [ 2, %bb3 ], [ 1, %bb1 ]
%cond1 = icmp eq i32 %vreg5, 0
br i1 %cond1, label %bb7, label %bb6
bb6: ; preds = %bb4
br label %bb7
bb7: ; preds = %bb4, %bb6
%vreg1 = phi i32 [ 2, %bb6 ], [ 1, %bb4 ]
%vreg2 = add i32 %vreg5, %vreg0
%vreg3 = add i32 %vreg1, %vreg2
%cond2 = icmp slt i32 %vreg3, 10
br i1 %cond2, label %bb1, label %bb8
bb8: ; preds = %bb7
ret i32 0
}
define i32 @bar(i32 %a, i32* %p) {
bb0:
br label %bb1
bb1: ; preds = %bb7, %bb0
%vreg0 = phi i32 [ 0, %bb0 ], [ %vreg3, %bb7 ]
%cond0 = icmp eq i32 %a, 0
br i1 %cond0, label %bb4, label %bb3
bb3: ; preds = %bb1
br label %bb4
bb4: ; preds = %bb1, %bb3
%vreg5 = phi i32 [ 2, %bb3 ], [ 1, %bb1 ]
%cond1 = icmp eq i32 %vreg5, 0
br i1 %cond1, label %bb7, label %bb6
bb6: ; preds = %bb4
br label %bb7
bb7: ; preds = %bb4, %bb6
%vreg1 = phi i32 [ 2, %bb6 ], [ 1, %bb4 ]
%vreg2 = add i32 %vreg5, %vreg0
store i32 %vreg0, i32* %p
%vreg3 = add i32 %vreg1, %vreg2
%cond2 = icmp slt i32 %vreg3, 10
br i1 %cond2, label %bb1, label %bb8
bb8: ; preds = %bb7
ret i32 0
}
...
---
# There is a recurrence formulated around %0, %10, and %3. Check that operands
# are commuted for ADD instructions in bb.5.bb7 so that the values involved in
# the recurrence are tied. This will remove redundant copy instruction.
name: foo
tracksRegLiveness: true
registers:
- { id: 0, class: gr32, preferred-register: '' }
- { id: 1, class: gr32, preferred-register: '' }
- { id: 2, class: gr32, preferred-register: '' }
- { id: 3, class: gr32, preferred-register: '' }
- { id: 4, class: gr32, preferred-register: '' }
- { id: 5, class: gr32, preferred-register: '' }
- { id: 6, class: gr32, preferred-register: '' }
- { id: 7, class: gr32, preferred-register: '' }
- { id: 8, class: gr32, preferred-register: '' }
- { id: 9, class: gr32, preferred-register: '' }
- { id: 10, class: gr32, preferred-register: '' }
- { id: 11, class: gr32, preferred-register: '' }
- { id: 12, class: gr32, preferred-register: '' }
liveins:
- { reg: '$edi', virtual-reg: '%4' }
body: |
bb.0.bb0:
successors: %bb.1(0x80000000)
liveins: $edi
%4 = COPY $edi
%5 = MOV32r0 implicit-def dead $eflags
bb.1.bb1:
successors: %bb.3(0x30000000), %bb.2(0x50000000)
; CHECK: %0:gr32 = PHI %5, %bb.0, %3, %bb.5
%0 = PHI %5, %bb.0, %3, %bb.5
%6 = MOV32ri 1
TEST32rr %4, %4, implicit-def $eflags
JE_1 %bb.3, implicit $eflags
JMP_1 %bb.2
bb.2.bb3:
successors: %bb.3(0x80000000)
%7 = MOV32ri 2
bb.3.bb4:
successors: %bb.5(0x30000000), %bb.4(0x50000000)
%1 = PHI %6, %bb.1, %7, %bb.2
TEST32rr %1, %1, implicit-def $eflags
JE_1 %bb.5, implicit $eflags
JMP_1 %bb.4
bb.4.bb6:
successors: %bb.5(0x80000000)
%9 = MOV32ri 2
bb.5.bb7:
successors: %bb.1(0x7c000000), %bb.6(0x04000000)
%2 = PHI %6, %bb.3, %9, %bb.4
%10 = ADD32rr %1, %0, implicit-def dead $eflags
; CHECK: %10:gr32 = ADD32rr
; CHECK-SAME: %0,
; CHECK-SAME: %1,
%3 = ADD32rr %2, killed %10, implicit-def dead $eflags
; CHECK: %3:gr32 = ADD32rr
; CHECK-SAME: %10,
; CHECK-SAME: %2,
%11 = SUB32ri8 %3, 10, implicit-def $eflags
JL_1 %bb.1, implicit $eflags
JMP_1 %bb.6
bb.6.bb8:
%12 = MOV32r0 implicit-def dead $eflags
$eax = COPY %12
RET 0, $eax
...
---
# Here a recurrence is formulated around %0, %11, and %3, but operands should
# not be commuted because %0 has a use outside of recurrence. This is to
# prevent the case of commuting operands ties the values with overlapping live
# ranges.
name: bar
tracksRegLiveness: true
registers:
- { id: 0, class: gr32, preferred-register: '' }
- { id: 1, class: gr32, preferred-register: '' }
- { id: 2, class: gr32, preferred-register: '' }
- { id: 3, class: gr32, preferred-register: '' }
- { id: 4, class: gr32, preferred-register: '' }
- { id: 5, class: gr64, preferred-register: '' }
- { id: 6, class: gr32, preferred-register: '' }
- { id: 7, class: gr32, preferred-register: '' }
- { id: 8, class: gr32, preferred-register: '' }
- { id: 9, class: gr32, preferred-register: '' }
- { id: 10, class: gr32, preferred-register: '' }
- { id: 11, class: gr32, preferred-register: '' }
- { id: 12, class: gr32, preferred-register: '' }
- { id: 13, class: gr32, preferred-register: '' }
liveins:
- { reg: '$edi', virtual-reg: '%4' }
- { reg: '$rsi', virtual-reg: '%5' }
body: |
bb.0.bb0:
successors: %bb.1(0x80000000)
liveins: $edi, $rsi
%5 = COPY $rsi
%4 = COPY $edi
%6 = MOV32r0 implicit-def dead $eflags
bb.1.bb1:
successors: %bb.3(0x30000000), %bb.2(0x50000000)
%0 = PHI %6, %bb.0, %3, %bb.5
; CHECK: %0:gr32 = PHI %6, %bb.0, %3, %bb.5
%7 = MOV32ri 1
TEST32rr %4, %4, implicit-def $eflags
JE_1 %bb.3, implicit $eflags
JMP_1 %bb.2
bb.2.bb3:
successors: %bb.3(0x80000000)
%8 = MOV32ri 2
bb.3.bb4:
successors: %bb.5(0x30000000), %bb.4(0x50000000)
%1 = PHI %7, %bb.1, %8, %bb.2
TEST32rr %1, %1, implicit-def $eflags
JE_1 %bb.5, implicit $eflags
JMP_1 %bb.4
bb.4.bb6:
successors: %bb.5(0x80000000)
%10 = MOV32ri 2
bb.5.bb7:
successors: %bb.1(0x7c000000), %bb.6(0x04000000)
%2 = PHI %7, %bb.3, %10, %bb.4
%11 = ADD32rr %1, %0, implicit-def dead $eflags
; CHECK: %11:gr32 = ADD32rr
; CHECK-SAME: %1,
; CHECK-SAME: %0,
MOV32mr %5, 1, $noreg, 0, $noreg, %0 :: (store 4 into %ir.p)
%3 = ADD32rr %2, killed %11, implicit-def dead $eflags
; CHECK: %3:gr32 = ADD32rr
; CHECK-SAME: %2,
; CHECK-SAME: %11,
%12 = SUB32ri8 %3, 10, implicit-def $eflags
JL_1 %bb.1, implicit $eflags
JMP_1 %bb.6
bb.6.bb8:
%13 = MOV32r0 implicit-def dead $eflags
$eax = COPY %13
RET 0, $eax
...