Files
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

71 lines
2.7 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc < %s -mtriple=x86_64-linux-gnu -mattr=avx512bf16 | FileCheck %s
define void @add(ptr %pa, ptr %pb, ptr %pc) nounwind {
; CHECK-LABEL: add:
; CHECK: # %bb.0:
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: movq %rdx, %rbx
; CHECK-NEXT: movzwl (%rsi), %eax
; CHECK-NEXT: shll $16, %eax
; CHECK-NEXT: vmovd %eax, %xmm0
; CHECK-NEXT: movzwl (%rdi), %eax
; CHECK-NEXT: shll $16, %eax
; CHECK-NEXT: vmovd %eax, %xmm1
; CHECK-NEXT: vaddss %xmm0, %xmm1, %xmm0
; CHECK-NEXT: callq __truncsfbf2@PLT
; CHECK-NEXT: vpextrw $0, %xmm0, (%rbx)
; CHECK-NEXT: popq %rbx
; CHECK-NEXT: retq
%a = load bfloat, ptr %pa
%b = load bfloat, ptr %pb
%add = fadd bfloat %a, %b
store bfloat %add, ptr %pc
ret void
}
define <4 x bfloat> @fptrunc_v4f32(<4 x float> %a) nounwind {
; CHECK-LABEL: fptrunc_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: pushq %rbp
; CHECK-NEXT: pushq %r14
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: subq $64, %rsp
; CHECK-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT: callq __truncsfbf2@PLT
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: vmovshdup (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[1,1,3,3]
; CHECK-NEXT: callq __truncsfbf2@PLT
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: vpshufd $255, (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[3,3,3,3]
; CHECK-NEXT: callq __truncsfbf2@PLT
; CHECK-NEXT: vmovdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: callq __truncsfbf2@PLT
; CHECK-NEXT: vpextrw $0, %xmm0, %ebx
; CHECK-NEXT: vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpextrw $0, %xmm0, %ebp
; CHECK-NEXT: vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpextrw $0, %xmm0, %r14d
; CHECK-NEXT: vpermilpd $1, (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[1,0]
; CHECK-NEXT: callq __truncsfbf2@PLT
; CHECK-NEXT: vpextrw $0, %xmm0, %eax
; CHECK-NEXT: vmovdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: vpinsrw $1, %r14d, %xmm0, %xmm0
; CHECK-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
; CHECK-NEXT: vpinsrw $3, %ebp, %xmm0, %xmm0
; CHECK-NEXT: vpinsrw $4, %ebx, %xmm0, %xmm0
; CHECK-NEXT: vpinsrw $5, %ebx, %xmm0, %xmm0
; CHECK-NEXT: vpinsrw $6, %ebx, %xmm0, %xmm0
; CHECK-NEXT: vpinsrw $7, %ebx, %xmm0, %xmm0
; CHECK-NEXT: addq $64, %rsp
; CHECK-NEXT: popq %rbx
; CHECK-NEXT: popq %r14
; CHECK-NEXT: popq %rbp
; CHECK-NEXT: retq
%b = fptrunc <4 x float> %a to <4 x bfloat>
ret <4 x bfloat> %b
}