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

107 lines
2.7 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -float-abi hard -mattr=+bf16,+fullfp16 < %s | FileCheck %s --check-prefix=HARD
; RUN: llc -float-abi soft -mattr=+bf16,+fullfp16 < %s | FileCheck %s --check-prefix=SOFT
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "armv8.6a-arm-none-eabi"
define bfloat @load_scalar_bf(ptr %addr) {
; HARD-LABEL: load_scalar_bf:
; HARD: @ %bb.0: @ %entry
; HARD-NEXT: vldr.16 s0, [r0]
; HARD-NEXT: bx lr
;
; SOFT-LABEL: load_scalar_bf:
; SOFT: @ %bb.0: @ %entry
; SOFT-NEXT: vldr.16 s0, [r0]
; SOFT-NEXT: vmov r0, s0
; SOFT-NEXT: bx lr
entry:
%0 = load bfloat, ptr %addr, align 2
ret bfloat %0
}
define void @store_scalar_bf(bfloat %v, ptr %addr) {
; HARD-LABEL: store_scalar_bf:
; HARD: @ %bb.0: @ %entry
; HARD-NEXT: vstr.16 s0, [r0]
; HARD-NEXT: bx lr
;
; SOFT-LABEL: store_scalar_bf:
; SOFT: @ %bb.0: @ %entry
; SOFT-NEXT: vmov.f16 s0, r0
; SOFT-NEXT: vstr.16 s0, [r1]
; SOFT-NEXT: bx lr
entry:
store bfloat %v, ptr %addr, align 2
ret void
}
define <4 x bfloat> @load_vector4_bf(ptr %addr) {
; HARD-LABEL: load_vector4_bf:
; HARD: @ %bb.0: @ %entry
; HARD-NEXT: vldr d0, [r0]
; HARD-NEXT: bx lr
;
; SOFT-LABEL: load_vector4_bf:
; SOFT: @ %bb.0: @ %entry
; SOFT-NEXT: vldr d16, [r0]
; SOFT-NEXT: vmov r0, r1, d16
; SOFT-NEXT: bx lr
entry:
%0 = load <4 x bfloat>, ptr %addr, align 8
ret <4 x bfloat> %0
}
define void @store_vector4_bf(<4 x bfloat> %v, ptr %addr) {
; HARD-LABEL: store_vector4_bf:
; HARD: @ %bb.0: @ %entry
; HARD-NEXT: vstr d0, [r0]
; HARD-NEXT: bx lr
;
; SOFT-LABEL: store_vector4_bf:
; SOFT: @ %bb.0: @ %entry
; SOFT-NEXT: strd r0, r1, [r2]
; SOFT-NEXT: bx lr
entry:
store <4 x bfloat> %v, ptr %addr, align 8
ret void
}
define <8 x bfloat> @load_vector8_bf(ptr %addr) {
; HARD-LABEL: load_vector8_bf:
; HARD: @ %bb.0: @ %entry
; HARD-NEXT: vld1.64 {d0, d1}, [r0]
; HARD-NEXT: bx lr
;
; SOFT-LABEL: load_vector8_bf:
; SOFT: @ %bb.0: @ %entry
; SOFT-NEXT: vld1.64 {d16, d17}, [r0]
; SOFT-NEXT: vmov r0, r1, d16
; SOFT-NEXT: vmov r2, r3, d17
; SOFT-NEXT: bx lr
entry:
%0 = load <8 x bfloat>, ptr %addr, align 8
ret <8 x bfloat> %0
}
define void @store_vector8_bf(<8 x bfloat> %v, ptr %addr) {
; HARD-LABEL: store_vector8_bf:
; HARD: @ %bb.0: @ %entry
; HARD-NEXT: vst1.64 {d0, d1}, [r0]
; HARD-NEXT: bx lr
;
; SOFT-LABEL: store_vector8_bf:
; SOFT: @ %bb.0: @ %entry
; SOFT-NEXT: vmov d17, r2, r3
; SOFT-NEXT: ldr r12, [sp]
; SOFT-NEXT: vmov d16, r0, r1
; SOFT-NEXT: vst1.64 {d16, d17}, [r12]
; SOFT-NEXT: bx lr
entry:
store <8 x bfloat> %v, ptr %addr, align 8
ret void
}