mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 03:53:04 +02:00
8681d4c5a2
Summary: If a function needs to allocate both callee-save stack memory and local stack memory, we currently decrement/increment the SP in two steps: first for the callee-save area, and then for the local stack area. This changes the code to allocate them both at once at the very beginning/end of the function. This has two benefits: 1) there is one fewer sub/add micro-op in the prologue/epilogue 2) the stack adjustment instructions act as a scheduling barrier, so moving them to the very beginning/end of the function increases post-RA scheduler's ability to move instructions (that only depend on argument registers) before any of the callee-save stores This change can cause an increase in instructions if the original local stack SP decrement could be folded into the first store to the stack. This occurs when the first local stack store is to stack offset 0. In this case we are trading off one more sub instruction for one fewer sub micro-op (along with benefits (2) and (3) above). Reviewers: t.p.northover Subscribers: aemerson, rengolin, mcrosier, llvm-commits Differential Revision: http://reviews.llvm.org/D18619 llvm-svn: 268746
238 lines
6.1 KiB
LLVM
238 lines
6.1 KiB
LLVM
; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -disable-fp-elim -tailcallopt | FileCheck %s -check-prefix CHECK-TAIL
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -disable-fp-elim | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -disable-fp-elim -tailcallopt -aarch64-redzone | FileCheck %s -check-prefix CHECK-TAIL-RZ
|
|
|
|
; Without tailcallopt fastcc still means the caller cleans up the
|
|
; stack, so try to make sure this is respected.
|
|
|
|
define fastcc void @func_stack0() {
|
|
; CHECK-LABEL: func_stack0:
|
|
; CHECK: sub sp, sp, #48
|
|
; CHECK: add x29, sp, #32
|
|
; CHECK: str w{{[0-9]+}}, [sp]
|
|
|
|
; CHECK-TAIL-LABEL: func_stack0:
|
|
; CHECK-TAIL: sub sp, sp, #48
|
|
; CHECK-TAIL-NEXT: stp x29, x30, [sp, #32]
|
|
; CHECK-TAIL-NEXT: add x29, sp, #32
|
|
; CHECK-TAIL: str w{{[0-9]+}}, [sp]
|
|
|
|
|
|
call fastcc void @func_stack8([8 x i32] undef, i32 42)
|
|
; CHECK: bl func_stack8
|
|
; CHECK-NOT: sub sp, sp,
|
|
|
|
; CHECK-TAIL: bl func_stack8
|
|
; CHECK-TAIL: sub sp, sp, #16
|
|
|
|
|
|
call fastcc void @func_stack32([8 x i32] undef, i128 0, i128 9)
|
|
; CHECK: bl func_stack32
|
|
; CHECK-NOT: sub sp, sp,
|
|
|
|
|
|
; CHECK-TAIL: bl func_stack32
|
|
; CHECK-TAIL: sub sp, sp, #32
|
|
|
|
|
|
call fastcc void @func_stack0()
|
|
; CHECK: bl func_stack0
|
|
; CHECK-NOT: sub sp, sp
|
|
|
|
|
|
; CHECK-TAIL: bl func_stack0
|
|
; CHECK-TAIL-NOT: sub sp, sp
|
|
|
|
ret void
|
|
; CHECK: ldp x29, x30, [sp, #32]
|
|
; CHECK-NEXT: add sp, sp, #48
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
; CHECK-TAIL: ldp x29, x30, [sp, #32]
|
|
; CHECK-TAIL-NEXT: add sp, sp, #48
|
|
; CHECK-TAIL-NEXT: ret
|
|
}
|
|
|
|
define fastcc void @func_stack8([8 x i32], i32 %stacked) {
|
|
; CHECK-LABEL: func_stack8:
|
|
; CHECK: sub sp, sp, #48
|
|
; CHECK: stp x29, x30, [sp, #32]
|
|
; CHECK: add x29, sp, #32
|
|
; CHECK: str w{{[0-9]+}}, [sp]
|
|
|
|
|
|
; CHECK-TAIL-LABEL: func_stack8:
|
|
; CHECK-TAIL: sub sp, sp, #48
|
|
; CHECK-TAIL: stp x29, x30, [sp, #32]
|
|
; CHECK-TAIL: add x29, sp, #32
|
|
; CHECK-TAIL: str w{{[0-9]+}}, [sp]
|
|
|
|
|
|
call fastcc void @func_stack8([8 x i32] undef, i32 42)
|
|
; CHECK: bl func_stack8
|
|
; CHECK-NOT: sub sp, sp,
|
|
|
|
|
|
; CHECK-TAIL: bl func_stack8
|
|
; CHECK-TAIL: sub sp, sp, #16
|
|
|
|
|
|
call fastcc void @func_stack32([8 x i32] undef, i128 0, i128 9)
|
|
; CHECK: bl func_stack32
|
|
; CHECK-NOT: sub sp, sp,
|
|
|
|
|
|
; CHECK-TAIL: bl func_stack32
|
|
; CHECK-TAIL: sub sp, sp, #32
|
|
|
|
|
|
call fastcc void @func_stack0()
|
|
; CHECK: bl func_stack0
|
|
; CHECK-NOT: sub sp, sp
|
|
|
|
; CHECK-TAIL: bl func_stack0
|
|
; CHECK-TAIL-NOT: sub sp, sp
|
|
|
|
ret void
|
|
; CHECK-NEXT: ldp x29, x30, [sp, #32]
|
|
; CHECK: add sp, sp, #48
|
|
; CHECK-NEXT: ret
|
|
|
|
|
|
; CHECK-TAIL: ldp x29, x30, [sp, #32]
|
|
; CHECK-TAIL-NEXT: add sp, sp, #64
|
|
; CHECK-TAIL-NEXT: ret
|
|
}
|
|
|
|
define fastcc void @func_stack32([8 x i32], i128 %stacked0, i128 %stacked1) {
|
|
; CHECK-LABEL: func_stack32:
|
|
; CHECK: add x29, sp, #32
|
|
|
|
; CHECK-TAIL-LABEL: func_stack32:
|
|
; CHECK-TAIL: add x29, sp, #32
|
|
|
|
|
|
call fastcc void @func_stack8([8 x i32] undef, i32 42)
|
|
; CHECK: bl func_stack8
|
|
; CHECK-NOT: sub sp, sp,
|
|
|
|
; CHECK-TAIL: bl func_stack8
|
|
; CHECK-TAIL: sub sp, sp, #16
|
|
|
|
|
|
call fastcc void @func_stack32([8 x i32] undef, i128 0, i128 9)
|
|
; CHECK: bl func_stack32
|
|
; CHECK-NOT: sub sp, sp,
|
|
|
|
|
|
; CHECK-TAIL: bl func_stack32
|
|
; CHECK-TAIL: sub sp, sp, #32
|
|
|
|
|
|
call fastcc void @func_stack0()
|
|
; CHECK: bl func_stack0
|
|
; CHECK-NOT: sub sp, sp
|
|
|
|
|
|
; CHECK-TAIL: bl func_stack0
|
|
; CHECK-TAIL-NOT: sub sp, sp
|
|
|
|
ret void
|
|
; CHECK: ldp x29, x30, [sp, #32]
|
|
; CHECK-NEXT: add sp, sp, #48
|
|
; CHECK-NEXT: ret
|
|
|
|
; CHECK-TAIL: ldp x29, x30, [sp, #32]
|
|
; CHECK-TAIL-NEXT: add sp, sp, #80
|
|
; CHECK-TAIL-NEXT: ret
|
|
}
|
|
|
|
; Check that arg stack pop is done after callee-save restore when no frame pointer is used.
|
|
define fastcc void @func_stack32_leaf([8 x i32], i128 %stacked0, i128 %stacked1) {
|
|
; CHECK-LABEL: func_stack32_leaf:
|
|
; CHECK: str x20, [sp, #-16]!
|
|
; CHECK: nop
|
|
; CHECK-NEXT: //NO_APP
|
|
; CHECK-NEXT: ldr x20, [sp], #16
|
|
; CHECK-NEXT: ret
|
|
|
|
; CHECK-TAIL-LABEL: func_stack32_leaf:
|
|
; CHECK-TAIL: str x20, [sp, #-16]!
|
|
; CHECK-TAIL: nop
|
|
; CHECK-TAIL-NEXT: //NO_APP
|
|
; CHECK-TAIL-NEXT: ldr x20, [sp], #16
|
|
; CHECK-TAIL-NEXT: add sp, sp, #32
|
|
; CHECK-TAIL-NEXT: ret
|
|
|
|
; CHECK-TAIL-RZ-LABEL: func_stack32_leaf:
|
|
; CHECK-TAIL-RZ: str x20, [sp, #-16]!
|
|
; CHECK-TAIL-RZ-NOT: sub sp, sp
|
|
; CHECK-TAIL-RZ: nop
|
|
; CHECK-TAIL-RZ-NEXT: //NO_APP
|
|
; CHECK-TAIL-RZ-NEXT: ldr x20, [sp], #16
|
|
; CHECK-TAIL-RZ-NEXT: add sp, sp, #32
|
|
; CHECK-TAIL-RZ-NEXT: ret
|
|
|
|
; Make sure there is a callee-save register to save/restore.
|
|
call void asm sideeffect "nop", "~{x20}"() nounwind
|
|
ret void
|
|
}
|
|
|
|
; Check that arg stack pop is done after callee-save restore when no frame pointer is used.
|
|
define fastcc void @func_stack32_leaf_local([8 x i32], i128 %stacked0, i128 %stacked1) {
|
|
; CHECK-LABEL: func_stack32_leaf_local:
|
|
; CHECK: sub sp, sp, #32
|
|
; CHECK-NEXT: str x20, [sp, #16]
|
|
; CHECK: nop
|
|
; CHECK-NEXT: //NO_APP
|
|
; CHECK-NEXT: ldr x20, [sp, #16]
|
|
; CHECK-NEXT: add sp, sp, #32
|
|
; CHECK-NEXT: ret
|
|
|
|
; CHECK-TAIL-LABEL: func_stack32_leaf_local:
|
|
; CHECK-TAIL: sub sp, sp, #32
|
|
; CHECK-TAIL-NEXT: str x20, [sp, #16]
|
|
; CHECK-TAIL: nop
|
|
; CHECK-TAIL-NEXT: //NO_APP
|
|
; CHECK-TAIL-NEXT: ldr x20, [sp, #16]
|
|
; CHECK-TAIL-NEXT: add sp, sp, #64
|
|
; CHECK-TAIL-NEXT: ret
|
|
|
|
; CHECK-TAIL-RZ-LABEL: func_stack32_leaf_local:
|
|
; CHECK-TAIL-RZ: str x20, [sp, #-16]!
|
|
; CHECK-TAIL-RZ-NOT: sub sp, sp
|
|
; CHECK-TAIL-RZ: nop
|
|
; CHECK-TAIL-RZ-NEXT: //NO_APP
|
|
; CHECK-TAIL-RZ-NEXT: ldr x20, [sp], #16
|
|
; CHECK-TAIL-RZ-NEXT: add sp, sp, #32
|
|
; CHECK-TAIL-RZ-NEXT: ret
|
|
|
|
%val0 = alloca [2 x i64], align 8
|
|
|
|
; Make sure there is a callee-save register to save/restore.
|
|
call void asm sideeffect "nop", "~{x20}"() nounwind
|
|
ret void
|
|
}
|
|
|
|
; Check that arg stack pop is done after callee-save restore when no frame pointer is used.
|
|
define fastcc void @func_stack32_leaf_local_nocs([8 x i32], i128 %stacked0, i128 %stacked1) {
|
|
; CHECK-LABEL: func_stack32_leaf_local_nocs:
|
|
; CHECK: sub sp, sp, #16
|
|
; CHECK: add sp, sp, #16
|
|
; CHECK-NEXT: ret
|
|
|
|
; CHECK-TAIL-LABEL: func_stack32_leaf_local_nocs:
|
|
; CHECK-TAIL: sub sp, sp, #16
|
|
; CHECK-TAIL: add sp, sp, #48
|
|
; CHECK-TAIL-NEXT: ret
|
|
|
|
; CHECK-TAIL-RZ-LABEL: func_stack32_leaf_local_nocs:
|
|
; CHECK-TAIL-RZ: add sp, sp, #32
|
|
; CHECK-TAIL-RZ-NEXT: ret
|
|
|
|
%val0 = alloca [2 x i64], align 8
|
|
|
|
ret void
|
|
}
|