| # RUN: llc -run-pass=prologepilog -reverse-csr-restore-seq -o - -mtriple=aarch64-- %s | FileCheck %s --check-prefixes=CHECK |
| # RUN: llc -start-before=prologepilog -stop-after=aarch64-ldst-opt -reverse-csr-restore-seq -o - -mtriple=aarch64-- %s | FileCheck %s --check-prefixes=CHECK |
| # |
| --- | |
| |
| define void @foo() nounwind { entry: unreachable } |
| |
| define void @bar() nounwind { entry: unreachable } |
| |
| define void @baz() nounwind { entry: unreachable } |
| |
| ... |
| --- |
| name: foo |
| # CHECK-LABEL: name: foo |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| $x19 = IMPLICIT_DEF |
| $x20 = IMPLICIT_DEF |
| $x21 = IMPLICIT_DEF |
| $x22 = IMPLICIT_DEF |
| $x23 = IMPLICIT_DEF |
| $x24 = IMPLICIT_DEF |
| $x25 = IMPLICIT_DEF |
| $x26 = IMPLICIT_DEF |
| |
| ; The local stack size is 0, so the last ldp in the sequence will also |
| ; restore the stack. |
| ; CHECK: $x24, $x23 = frame-destroy LDPXi $sp, 2 |
| ; CHECK-NEXT: $x22, $x21 = frame-destroy LDPXi $sp, 4 |
| ; CHECK-NEXT: $x20, $x19 = frame-destroy LDPXi $sp, 6 |
| |
| ; The ldp and the stack increment get merged even before |
| ; the load-store optimizer. |
| ; CHECK-NEXT: early-clobber $sp, $x26, $x25 = frame-destroy LDPXpost $sp, 8 |
| |
| RET_ReallyLR |
| ... |
| --- |
| name: bar |
| # CHECK-LABEL: name: bar |
| tracksRegLiveness: true |
| stack: |
| - { id : 0, size: 8, alignment: 4, |
| stack-id: default, callee-saved-register: '', callee-saved-restored: true, |
| local-offset: -4, debug-info-variable: '', debug-info-expression: '', |
| debug-info-location: '' } |
| |
| body: | |
| bb.0: |
| $x19 = IMPLICIT_DEF |
| $x20 = IMPLICIT_DEF |
| $x21 = IMPLICIT_DEF |
| $x22 = IMPLICIT_DEF |
| $x23 = IMPLICIT_DEF |
| $x24 = IMPLICIT_DEF |
| $x25 = IMPLICIT_DEF |
| $x26 = IMPLICIT_DEF |
| |
| ; The local stack size is not 0, and we can combine the CSR stack size with |
| ; the local stack size. This results in rewriting the offsets for all the |
| ; save/restores and forbids us to merge the stack adjustment and the last pop. |
| ; In this case, there is no point of moving the first CSR pair at the end. |
| ; We do it anyway, as it's a small price to pay for the resulting |
| ; simplification in the epilogue emission code. |
| ; CHECK: $x24, $x23 = frame-destroy LDPXi $sp, 4 |
| ; CHECK-NEXT: $x22, $x21 = frame-destroy LDPXi $sp, 6 |
| ; CHECK-NEXT: $x20, $x19 = frame-destroy LDPXi $sp, 8 |
| ; CHECK-NEXT: $x26, $x25 = frame-destroy LDPXi $sp, 2 |
| ; CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 80, 0 |
| RET_ReallyLR |
| ... |
| --- |
| # Check that the load from the offset 0 is moved at the end even when hasFP is |
| # false. |
| name: baz |
| # CHECK-LABEL: name: baz |
| alignment: 4 |
| tracksRegLiveness: true |
| frameInfo: |
| adjustsStack: true |
| hasCalls: true |
| body: | |
| bb.0: |
| successors: %bb.1 |
| |
| $x0 = IMPLICIT_DEF |
| $x20 = IMPLICIT_DEF |
| $x21 = IMPLICIT_DEF |
| |
| ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp |
| BL @foo, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0 |
| ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp |
| B %bb.1 |
| |
| bb.1: |
| ; CHECK: $x21, $x20 = frame-destroy LDPXi $sp, 2 |
| ; CHECK-NEXT: early-clobber $sp, $lr = frame-destroy LDRXpost $sp, 32 |
| RET_ReallyLR |
| ... |