11b0401926
Currently, the AMDGPU backend bumps the Stack Pointer by fixed size offsets in the prolog of device functions, and restores it by the same amount in the epilog. Prolog: sp += frameSize Epilog: sp -= frameSize If a function has dynamic stack realignment, Prolog: sp += frameSize + max_alignment Epilog: sp -= frameSize + max_alignment These calculations are not optimal in case of dynamic stack realignment, and completely fail in case of dynamic stack readjustment. This patch uses the saved Frame Pointer to restore SP. Prolog: fp = sp sp += frameSize Epilog: sp = fp In case of dynamic stack realignment, SP is restored from the saved Base Pointer. Prolog: fp = sp + (max_alignment - 1) fp = fp & (-max_alignment) bp = sp sp += frameSize + max_alignment Epilog: sp = bp (Note: The presence of BP has been enforced in case of any dynamic stack realignment.) --------- Co-authored-by: Pravin Jagtap <Pravin.Jagtap@amd.com> Co-authored-by: Matt Arsenault <arsenm2@gmail.com>
57 lines
1.9 KiB
LLVM
57 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn %s -o - | FileCheck %s
|
|
|
|
@foo_a = alias void (ptr), ptr @foo
|
|
@bar_a = alias void (ptr), ptr @foo_a
|
|
|
|
define void @foo() {
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: ; %bb.0: ; %entry
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
entry:
|
|
ret void
|
|
}
|
|
|
|
define void @bar() {
|
|
; CHECK-LABEL: bar:
|
|
; CHECK: ; %bb.0: ; %entry
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_mov_b32 s16, s33
|
|
; CHECK-NEXT: s_mov_b32 s33, s32
|
|
; CHECK-NEXT: s_or_saveexec_b64 s[18:19], -1
|
|
; CHECK-NEXT: buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: s_mov_b64 exec, s[18:19]
|
|
; CHECK-NEXT: s_waitcnt expcnt(0)
|
|
; CHECK-NEXT: v_writelane_b32 v40, s16, 2
|
|
; CHECK-NEXT: s_addk_i32 s32, 0x400
|
|
; CHECK-NEXT: v_writelane_b32 v40, s30, 0
|
|
; CHECK-NEXT: v_writelane_b32 v40, s31, 1
|
|
; CHECK-NEXT: s_getpc_b64 s[16:17]
|
|
; CHECK-NEXT: s_add_u32 s16, s16, bar_a@gotpcrel32@lo+4
|
|
; CHECK-NEXT: s_addc_u32 s17, s17, bar_a@gotpcrel32@hi+12
|
|
; CHECK-NEXT: s_load_dwordx2 s[16:17], s[16:17], 0x0
|
|
; CHECK-NEXT: v_mov_b32_e32 v0, 0
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, 0
|
|
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
|
|
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
|
|
; CHECK-NEXT: v_readlane_b32 s31, v40, 1
|
|
; CHECK-NEXT: v_readlane_b32 s30, v40, 0
|
|
; CHECK-NEXT: s_mov_b32 s32, s33
|
|
; CHECK-NEXT: v_readlane_b32 s4, v40, 2
|
|
; CHECK-NEXT: s_or_saveexec_b64 s[6:7], -1
|
|
; CHECK-NEXT: buffer_load_dword v40, off, s[0:3], s33 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: s_mov_b64 exec, s[6:7]
|
|
; CHECK-NEXT: s_mov_b32 s33, s4
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0)
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
entry:
|
|
call void @bar_a(ptr null)
|
|
ret void
|
|
}
|
|
|
|
; UTC_ARGS: --disable
|
|
; CHECK: .set foo_a, foo
|
|
; CHECK: .set bar_a, foo_a
|
|
; UTC_ARGS: --enable
|