db158c7c83
Refresh of the generic scheduling model to use A510 instead of A55. Main benefits are to the little core, and introducing SVE scheduling information. Changes tested on various OoO cores, no performance degradation is seen. Differential Revision: https://reviews.llvm.org/D156799
65 lines
2.0 KiB
LLVM
65 lines
2.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -verify-machineinstrs -o - %s | FileCheck %s
|
|
; LSR used to pick a sub-optimal solution due to the target responding
|
|
; conservatively to isLegalAddImmediate for negative values.
|
|
|
|
declare void @foo(i32)
|
|
|
|
define void @test(i32 %px) {
|
|
; CHECK-LABEL: test:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w30, -32
|
|
; CHECK-NEXT: subs w8, w0, #1
|
|
; CHECK-NEXT: mov w19, w0
|
|
; CHECK-NEXT: csel w20, wzr, w8, lt
|
|
; CHECK-NEXT: b .LBB0_2
|
|
; CHECK-NEXT: .LBB0_1: // %for.inc
|
|
; CHECK-NEXT: // in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: cmp w20, w19
|
|
; CHECK-NEXT: add w20, w20, #1
|
|
; CHECK-NEXT: b.gt .LBB0_4
|
|
; CHECK-NEXT: .LBB0_2: // %for.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: cmp w19, w20
|
|
; CHECK-NEXT: b.eq .LBB0_1
|
|
; CHECK-NEXT: // %bb.3: // %if.then3
|
|
; CHECK-NEXT: // in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: mov w0, w20
|
|
; CHECK-NEXT: bl foo
|
|
; CHECK-NEXT: b .LBB0_1
|
|
; CHECK-NEXT: .LBB0_4: // %for.cond.cleanup
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%sub = add nsw i32 %px, -1
|
|
%cmp = icmp slt i32 %px, 1
|
|
%.sub = select i1 %cmp, i32 0, i32 %sub
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%x.015 = phi i32 [ %inc, %for.inc ], [ %.sub, %entry ]
|
|
%cmp2 = icmp eq i32 %x.015, %px
|
|
br i1 %cmp2, label %for.inc, label %if.then3
|
|
|
|
if.then3:
|
|
tail call void @foo(i32 %x.015)
|
|
br label %for.inc
|
|
|
|
for.inc:
|
|
%inc = add nsw i32 %x.015, 1
|
|
%cmp1 = icmp sgt i32 %x.015, %px
|
|
br i1 %cmp1, label %for.cond.cleanup.loopexit, label %for.body
|
|
|
|
for.cond.cleanup.loopexit:
|
|
br label %for.cond.cleanup
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|