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
79 lines
2.9 KiB
LLVM
79 lines
2.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc < %s | FileCheck %s
|
|
|
|
; Verify that the following code can be compiled without +sme, because if the
|
|
; call is not entered in streaming-SVE mode at runtime, the codepath leading
|
|
; to the smstop/smstart pair will not be executed either.
|
|
|
|
target triple = "aarch64"
|
|
|
|
define void @streaming_compatible() #0 {
|
|
; CHECK-LABEL: streaming_compatible:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp d15, d14, [sp, #-80]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp d13, d12, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp d11, d10, [sp, #32] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp d9, d8, [sp, #48] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp x30, x19, [sp, #64] // 16-byte Folded Spill
|
|
; CHECK-NEXT: bl __arm_sme_state
|
|
; CHECK-NEXT: mov x19, x0
|
|
; CHECK-NEXT: tbz w19, #0, .LBB0_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: smstop sm
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: bl non_streaming
|
|
; CHECK-NEXT: tbz w19, #0, .LBB0_4
|
|
; CHECK-NEXT: // %bb.3:
|
|
; CHECK-NEXT: smstart sm
|
|
; CHECK-NEXT: .LBB0_4:
|
|
; CHECK-NEXT: ldp x30, x19, [sp, #64] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d9, d8, [sp, #48] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d11, d10, [sp, #32] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d13, d12, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d15, d14, [sp], #80 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @non_streaming()
|
|
ret void
|
|
}
|
|
|
|
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 Spill
|
|
; CHECK-NEXT: bl __arm_sme_state
|
|
; CHECK-NEXT: mov x19, x0
|
|
; 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 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" }
|