b8d6659bff
* Do not use profile data when flipping a branch condition when optimizing for size. This should improving outlining and ICF due to more uniform instruction sequences. * Refactor `optimizeBranches()` to use early `continue`s * Use the correct debug location for `insertBranch()`
89 lines
2.1 KiB
LLVM
89 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple=aarch64 | FileCheck %s
|
|
|
|
; When consuming profile data we sometimes flip a branch to improve runtime
|
|
; performance. If we are optimizing for size, we avoid changing the branch to
|
|
; improve outlining and ICF.
|
|
|
|
define i8 @foo_optsize(i32 %v4) optsize {
|
|
; CHECK-LABEL: foo_optsize:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: cbz wzr, .LBB0_2
|
|
; CHECK-NEXT: .LBB0_1:
|
|
; CHECK-NEXT: mov w0, wzr
|
|
; CHECK-NEXT: ret
|
|
; CHECK-NEXT: .LBB0_2: // %b1
|
|
; CHECK-NEXT: cbnz w0, .LBB0_4
|
|
; CHECK-NEXT: .LBB0_3: // %b2
|
|
; CHECK-NEXT: mov w0, #1 // =0x1
|
|
; CHECK-NEXT: ret
|
|
; CHECK-NEXT: .LBB0_4: // %b1
|
|
; CHECK-NEXT: cmp w0, #1
|
|
; CHECK-NEXT: b.ne .LBB0_1
|
|
; CHECK-NEXT: // %bb.5: // %b3
|
|
; CHECK-NEXT: cbz wzr, .LBB0_1
|
|
; CHECK-NEXT: b .LBB0_3
|
|
entry:
|
|
%v2 = icmp eq i32 0, 0
|
|
br i1 %v2, label %b1, label %b4
|
|
|
|
b1:
|
|
switch i32 %v4, label %b4 [
|
|
i32 1, label %b3
|
|
i32 0, label %b2
|
|
], !prof !0
|
|
|
|
b2:
|
|
br label %b4
|
|
|
|
b3:
|
|
%v3 = icmp eq i32 0, 0
|
|
br i1 %v3, label %b4, label %b2
|
|
|
|
b4:
|
|
%v16 = phi i8 [ 1, %b2 ], [ 0, %entry ], [ 0, %b3 ], [ 0, %b1 ]
|
|
ret i8 %v16
|
|
}
|
|
|
|
define i8 @foo_optspeed(i32 %v4) {
|
|
; CHECK-LABEL: foo_optspeed:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: cbz wzr, .LBB1_2
|
|
; CHECK-NEXT: .LBB1_1:
|
|
; CHECK-NEXT: mov w0, wzr
|
|
; CHECK-NEXT: ret
|
|
; CHECK-NEXT: .LBB1_2: // %b1
|
|
; CHECK-NEXT: cbnz w0, .LBB1_4
|
|
; CHECK-NEXT: .LBB1_3: // %b2
|
|
; CHECK-NEXT: mov w0, #1 // =0x1
|
|
; CHECK-NEXT: ret
|
|
; CHECK-NEXT: .LBB1_4: // %b1
|
|
; CHECK-NEXT: cmp w0, #1
|
|
; CHECK-NEXT: b.ne .LBB1_1
|
|
; CHECK-NEXT: // %bb.5: // %b3
|
|
; CHECK-NEXT: cbnz wzr, .LBB1_3
|
|
; CHECK-NEXT: b .LBB1_1
|
|
entry:
|
|
%v2 = icmp eq i32 0, 0
|
|
br i1 %v2, label %b1, label %b4
|
|
|
|
b1:
|
|
switch i32 %v4, label %b4 [
|
|
i32 1, label %b3
|
|
i32 0, label %b2
|
|
], !prof !0
|
|
|
|
b2:
|
|
br label %b4
|
|
|
|
b3:
|
|
%v3 = icmp eq i32 0, 0
|
|
br i1 %v3, label %b4, label %b2
|
|
|
|
b4:
|
|
%v16 = phi i8 [ 1, %b2 ], [ 0, %entry ], [ 0, %b3 ], [ 0, %b1 ]
|
|
ret i8 %v16
|
|
}
|
|
|
|
!0 = !{!"branch_weights", i32 5, i32 5, i32 100}
|