mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-22 07:32:48 +00:00
b96e833817
This patch minimizes the number of nops that must be emitted on X86 to satisfy stackmap shadow constraints. To minimize the number of nops inserted, the X86AsmPrinter now records the size of the most recent stackmap's shadow in the StackMapShadowTracker class, and tracks the number of instruction bytes emitted since the that stackmap instruction was encountered. Padding is emitted (if it is required at all) immediately before the next stackmap/patchpoint instruction, or at the end of the basic block. This optimization should reduce code-size and improve performance for people using the llvm stackmap intrinsic on X86. <rdar://problem/14959522> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213892 91177308-0d34-0410-b5e6-96231b3b80d8
21 lines
705 B
LLVM
21 lines
705 B
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -disable-fp-elim | FileCheck %s
|
|
|
|
; Check that the X86 stackmap shadow optimization is only outputting a 1-byte
|
|
; nop here. 8-bytes are requested, but 7 are covered by the code for the call to
|
|
; bar, the frame teardown and the return.
|
|
define void @shadow_optimization_test() {
|
|
entry:
|
|
; CHECK-LABEL: shadow_optimization_test:
|
|
; CHECK: callq _bar
|
|
; CHECK-NOT: nop
|
|
; CHECK: callq _bar
|
|
; CHECK: retq
|
|
; CHECK: nop
|
|
call void @bar()
|
|
tail call void (i64, i32, ...)* @llvm.experimental.stackmap(i64 0, i32 8)
|
|
call void @bar()
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.experimental.stackmap(i64, i32, ...)
|
|
declare void @bar() |