Skip to content

[AArch64][SME] Make coalescer barrier available without +sme. #85311

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.

Sign up for GitHub

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 18, 2024
Merged

[AArch64][SME] Make coalescer barrier available without +sme. #85311

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,6 +192,8 @@ def : Pat<(int_aarch64_sme_set_tpidr2 i64:$val),
def : Pat<(i64 (int_aarch64_sme_get_tpidr2)),
(MRS 0xde85)>;

} // End let Predicates = [HasSME]

multiclass CoalescerBarrierPseudo<RegisterClass rc, list<ValueType> vts> {
def NAME : Pseudo<(outs rc:$dst), (ins rc:$src), []>, Sched<[]> {
let Constraints = "$dst = $src";
Expand All @@ -211,8 +213,6 @@ multiclass CoalescerBarriers {

defm COALESCER_BARRIER : CoalescerBarriers;

} // End let Predicates = [HasSME]

// Pseudo to match to smstart/smstop. This expands:
//
// pseudonode (pstate_za|pstate_sm), before_call, expected_value
Expand Down
39 changes: 39 additions & 0 deletions llvm/test/CodeGen/AArch64/sme-call-streaming-compatible-to-normal-fn-wihout-sme-attr.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,4 +38,43 @@ define void @streaming_compatible() #0 {

declare void @non_streaming()


; Verify that COALESCER_BARRIER is also supported without +sme.

define void @streaming_compatible_arg(float %f) #0 {
; CHECK-LABEL: streaming_compatible_arg:
; CHECK: // %bb.0:
; CHECK-NEXT: sub sp, sp, #96
; CHECK-NEXT: stp d15, d14, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: stp d13, d12, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT: stp d11, d10, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT: stp d9, d8, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT: stp x30, x19, [sp, #80] // 16-byte Folded Spill
; CHECK-NEXT: str s0, [sp, #12] // 4-byte Folded Spill
; CHECK-NEXT: bl __arm_sme_state
; CHECK-NEXT: ldr s0, [sp, #12] // 4-byte Folded Reload
; CHECK-NEXT: and x19, x0, #0x1
; CHECK-NEXT: str s0, [sp, #12] // 4-byte Folded Spill
; CHECK-NEXT: tbz w19, #0, .LBB1_2
; CHECK-NEXT: // %bb.1:
; CHECK-NEXT: smstop sm
; CHECK-NEXT: .LBB1_2:
; CHECK-NEXT: ldr s0, [sp, #12] // 4-byte Folded Reload
; CHECK-NEXT: bl non_streaming
; CHECK-NEXT: tbz w19, #0, .LBB1_4
; CHECK-NEXT: // %bb.3:
; CHECK-NEXT: smstart sm
; CHECK-NEXT: .LBB1_4:
; CHECK-NEXT: ldp x30, x19, [sp, #80] // 16-byte Folded Reload
; CHECK-NEXT: ldp d9, d8, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT: ldp d11, d10, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT: ldp d13, d12, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT: ldp d15, d14, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: add sp, sp, #96
; CHECK-NEXT: ret
call void @non_streaming(float %f)
ret void
}


attributes #0 = { nounwind "aarch64_pstate_sm_compatible" }