mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 20:43:44 +02:00
f156ca7ef2
When we're outlining a sequence that ends in a call, we can save up to three instructions in the outlined function by turning the call into a tail-call. I refer to this as thunk outlining because the resulting outlined function looks like a thunk; suggestions welcome for a better name. In addition to making the outlined function shorter, thunk outlining allows outlining calls which would otherwise be illegal to outline: we don't need to save/restore LR, so we don't need to prove anything about the stack access patterns of the callee. To make this work effectively, I also added MachineOutlinerInstrType::LegalTerminator to the generic MachineOutliner code; this allows treating an arbitrary instruction as a terminator in the suffix tree. Differential Revision: https://reviews.llvm.org/D47173 llvm-svn: 333015
48 lines
1.5 KiB
LLVM
48 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -enable-machine-outliner -verify-machineinstrs | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64-pc-linux-gnu"
|
|
|
|
declare i32 @thunk_called_fn(i32, i32, i32, i32)
|
|
|
|
define i32 @a() {
|
|
; CHECK-LABEL: a:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: bl OUTLINED_FUNCTION_0
|
|
; CHECK-NEXT: add w0, w0, #8 // =8
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%call = tail call i32 @thunk_called_fn(i32 1, i32 2, i32 3, i32 4)
|
|
%cx = add i32 %call, 8
|
|
ret i32 %cx
|
|
}
|
|
|
|
define i32 @b() {
|
|
; CHECK-LABEL: b:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: bl OUTLINED_FUNCTION_0
|
|
; CHECK-NEXT: add w0, w0, #88 // =88
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%call = tail call i32 @thunk_called_fn(i32 1, i32 2, i32 3, i32 4)
|
|
%cx = add i32 %call, 88
|
|
ret i32 %cx
|
|
}
|
|
|
|
; CHECK-LABEL: OUTLINED_FUNCTION_0:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: orr w0, wzr, #0x1
|
|
; CHECK-NEXT: orr w1, wzr, #0x2
|
|
; CHECK-NEXT: orr w2, wzr, #0x3
|
|
; CHECK-NEXT: orr w3, wzr, #0x4
|
|
; CHECK-NEXT: b thunk_called_fn
|