derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
75 lines
2.4 KiB
LLVM
75 lines
2.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -O0 -mtriple=aarch64-linux-gnu -mattr=+sme -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
declare void @shared_za_callee() "aarch64_inout_za"
|
|
|
|
define void @private_za() "aarch64_new_za" {
|
|
; CHECK-LABEL: private_za:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: cbnz x8, .LBB0_1
|
|
; CHECK-NEXT: b .LBB0_2
|
|
; CHECK-NEXT: .LBB0_1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_save
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: zero {za}
|
|
; CHECK-NEXT: b .LBB0_2
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: smstop za
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; Note: This test must run at -O0 as otherwise the multiple exits are optimized out.
|
|
define i32 @private_za_multiple_exit(i32 %a, i32 %b, i64 %cond) "aarch64_new_za" {
|
|
; CHECK-LABEL: private_za_multiple_exit:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: str w1, [sp, #8] // 4-byte Spill
|
|
; CHECK-NEXT: str w0, [sp, #12] // 4-byte Spill
|
|
; CHECK-NEXT: subs x8, x2, #1
|
|
; CHECK-NEXT: b.ne .LBB1_2
|
|
; CHECK-NEXT: b .LBB1_1
|
|
; CHECK-NEXT: .LBB1_1: // %if.else
|
|
; CHECK-NEXT: ldr w8, [sp, #12] // 4-byte Reload
|
|
; CHECK-NEXT: ldr w9, [sp, #8] // 4-byte Reload
|
|
; CHECK-NEXT: add w0, w8, w9
|
|
; CHECK-NEXT: add sp, sp, #16
|
|
; CHECK-NEXT: ret
|
|
; CHECK-NEXT: .LBB1_2: // %if.end
|
|
; CHECK-NEXT: ldr w8, [sp, #12] // 4-byte Reload
|
|
; CHECK-NEXT: ldr w9, [sp, #8] // 4-byte Reload
|
|
; CHECK-NEXT: subs w0, w8, w9
|
|
; CHECK-NEXT: add sp, sp, #16
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%tobool = icmp eq i64 %cond, 1
|
|
br i1 %tobool, label %if.else, label %if.end
|
|
|
|
if.else:
|
|
%add = add i32 %a, %b
|
|
ret i32 %add
|
|
|
|
if.end:
|
|
%sub = sub i32 %a, %b
|
|
ret i32 %sub
|
|
}
|
|
|
|
; In simple cases like this we should omit all ZA setup.
|
|
define i32 @private_za_trivially_does_not_use_za(i32 %x) "aarch64_new_za" {
|
|
; CHECK-LABEL: private_za_trivially_does_not_use_za:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: add w0, w0, w0
|
|
; CHECK-NEXT: ret
|
|
%ret = add i32 %x, %x
|
|
ret i32 %ret
|
|
}
|