Skip to content

[AArch64][SME2] Don't preserve ZT0 around SME ABI routines #132722

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 25, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion llvm/lib/Target/AArch64/Utils/AArch64SMEAttributes.h
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,8 @@ class SMEAttrs {
bool hasZT0State() const { return isNewZT0() || sharesZT0(); }
bool requiresPreservingZT0(const SMEAttrs &Callee) const {
return hasZT0State() && !Callee.sharesZT0() &&
!Callee.hasAgnosticZAInterface();
!Callee.hasAgnosticZAInterface() &&
!(Callee.Bitmask & SME_ABI_Routine);
}
bool requiresDisablingZABeforeCall(const SMEAttrs &Callee) const {
return hasZT0State() && !hasZAState() && Callee.hasPrivateZAInterface() &&
Expand Down
9 changes: 2 additions & 7 deletions llvm/test/CodeGen/AArch64/sme-disable-gisel-fisel.ll
Original file line number Diff line number Diff line change
Expand Up @@ -475,16 +475,12 @@ declare double @zt0_shared_callee(double) "aarch64_inout_zt0"
define double @zt0_new_caller_to_zt0_shared_callee(double %x) nounwind noinline optnone "aarch64_new_zt0" {
; CHECK-COMMON-LABEL: zt0_new_caller_to_zt0_shared_callee:
; CHECK-COMMON: // %bb.0: // %prelude
; CHECK-COMMON-NEXT: sub sp, sp, #80
; CHECK-COMMON-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
; CHECK-COMMON-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-COMMON-NEXT: mrs x8, TPIDR2_EL0
; CHECK-COMMON-NEXT: cbz x8, .LBB13_2
; CHECK-COMMON-NEXT: b .LBB13_1
; CHECK-COMMON-NEXT: .LBB13_1: // %save.za
; CHECK-COMMON-NEXT: mov x8, sp
; CHECK-COMMON-NEXT: str zt0, [x8]
; CHECK-COMMON-NEXT: bl __arm_tpidr2_save
; CHECK-COMMON-NEXT: ldr zt0, [x8]
; CHECK-COMMON-NEXT: msr TPIDR2_EL0, xzr
; CHECK-COMMON-NEXT: b .LBB13_2
; CHECK-COMMON-NEXT: .LBB13_2: // %entry
Expand All @@ -495,8 +491,7 @@ define double @zt0_new_caller_to_zt0_shared_callee(double %x) nounwind noinline
; CHECK-COMMON-NEXT: fmov d1, x8
; CHECK-COMMON-NEXT: fadd d0, d0, d1
; CHECK-COMMON-NEXT: smstop za
; CHECK-COMMON-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-COMMON-NEXT: add sp, sp, #80
; CHECK-COMMON-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-COMMON-NEXT: ret
entry:
%call = call double @zt0_shared_callee(double %x)
Expand Down
61 changes: 42 additions & 19 deletions llvm/test/CodeGen/AArch64/sme-zt0-state.ll
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@ define void @za_zt0_shared_caller_za_zt0_shared_callee() "aarch64_inout_za" "aar
ret void;
}

; New-ZA Callee
; New-ZT0 Callee

; Expect spill & fill of ZT0 around call
; Expect smstop/smstart za around call
Expand All @@ -134,6 +134,39 @@ define void @zt0_in_caller_zt0_new_callee() "aarch64_in_zt0" nounwind {
ret void;
}

; New-ZT0 Callee

; Expect commit of lazy-save if ZA is dormant
; Expect smstart ZA & clear ZT0
; Expect spill & fill of ZT0 around call
; Before return, expect smstop ZA
define void @zt0_new_caller_zt0_new_callee() "aarch64_new_zt0" nounwind {
; CHECK-LABEL: zt0_new_caller_zt0_new_callee:
; CHECK: // %bb.0: // %prelude
; CHECK-NEXT: sub sp, sp, #80
; CHECK-NEXT: stp x30, x19, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT: mrs x8, TPIDR2_EL0
; CHECK-NEXT: cbz x8, .LBB6_2
; CHECK-NEXT: // %bb.1: // %save.za
; CHECK-NEXT: bl __arm_tpidr2_save
; CHECK-NEXT: msr TPIDR2_EL0, xzr
; CHECK-NEXT: .LBB6_2:
; CHECK-NEXT: smstart za
; CHECK-NEXT: zero { zt0 }
; CHECK-NEXT: mov x19, sp
; CHECK-NEXT: str zt0, [x19]
; CHECK-NEXT: smstop za
; CHECK-NEXT: bl callee
; CHECK-NEXT: smstart za
; CHECK-NEXT: ldr zt0, [x19]
; CHECK-NEXT: smstop za
; CHECK-NEXT: ldp x30, x19, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT: add sp, sp, #80
; CHECK-NEXT: ret
call void @callee() "aarch64_new_zt0";
ret void;
}

;
; New-ZA Caller
;
Expand All @@ -144,23 +177,18 @@ define void @zt0_in_caller_zt0_new_callee() "aarch64_in_zt0" nounwind {
define void @zt0_new_caller() "aarch64_new_zt0" nounwind {
; CHECK-LABEL: zt0_new_caller:
; CHECK: // %bb.0: // %prelude
; CHECK-NEXT: sub sp, sp, #80
; CHECK-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: mrs x8, TPIDR2_EL0
; CHECK-NEXT: cbz x8, .LBB6_2
; CHECK-NEXT: cbz x8, .LBB7_2
; CHECK-NEXT: // %bb.1: // %save.za
; CHECK-NEXT: mov x8, sp
; CHECK-NEXT: str zt0, [x8]
; CHECK-NEXT: bl __arm_tpidr2_save
; CHECK-NEXT: ldr zt0, [x8]
; CHECK-NEXT: msr TPIDR2_EL0, xzr
; CHECK-NEXT: .LBB6_2:
; CHECK-NEXT: .LBB7_2:
; CHECK-NEXT: smstart za
; CHECK-NEXT: zero { zt0 }
; CHECK-NEXT: bl callee
; CHECK-NEXT: smstop za
; CHECK-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-NEXT: add sp, sp, #80
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
call void @callee() "aarch64_in_zt0";
ret void;
Expand All @@ -172,24 +200,19 @@ define void @zt0_new_caller() "aarch64_new_zt0" nounwind {
define void @new_za_zt0_caller() "aarch64_new_za" "aarch64_new_zt0" nounwind {
; CHECK-LABEL: new_za_zt0_caller:
; CHECK: // %bb.0: // %prelude
; CHECK-NEXT: sub sp, sp, #80
; CHECK-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: mrs x8, TPIDR2_EL0
; CHECK-NEXT: cbz x8, .LBB7_2
; CHECK-NEXT: cbz x8, .LBB8_2
; CHECK-NEXT: // %bb.1: // %save.za
; CHECK-NEXT: mov x8, sp
; CHECK-NEXT: str zt0, [x8]
; CHECK-NEXT: bl __arm_tpidr2_save
; CHECK-NEXT: ldr zt0, [x8]
; CHECK-NEXT: msr TPIDR2_EL0, xzr
; CHECK-NEXT: .LBB7_2:
; CHECK-NEXT: .LBB8_2:
; CHECK-NEXT: smstart za
; CHECK-NEXT: zero {za}
; CHECK-NEXT: zero { zt0 }
; CHECK-NEXT: bl callee
; CHECK-NEXT: smstop za
; CHECK-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-NEXT: add sp, sp, #80
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
call void @callee() "aarch64_inout_za" "aarch64_in_zt0";
ret void;
Expand Down