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
139 lines
6.1 KiB
LLVM
139 lines
6.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve,+sme < %s | FileCheck %s
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -force-streaming < %s | FileCheck %s
|
|
|
|
;
|
|
; FMLALB (Vectors)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlalb_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlalb_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlalb z0.s, z1.h, z2.h
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalb.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLALB (Indexed)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlalb_lane_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlalb_lane_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlalb z0.s, z1.h, z2.h[0]
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalb.lane.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c,
|
|
i32 0)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLALT (Vectors)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlalt_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlalt_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlalt z0.s, z1.h, z2.h
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalt.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLALT (Indexed)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlalt_lane_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlalt_lane_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlalt z0.s, z1.h, z2.h[1]
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalt.lane.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c,
|
|
i32 1)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLSLB (Vectors)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlslb_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlslb_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlslb z0.s, z1.h, z2.h
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslb.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLSLB (Indexed)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlslb_lane_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlslb_lane_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlslb z0.s, z1.h, z2.h[2]
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslb.lane.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c,
|
|
i32 2)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLSLT (Vectors)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlslt_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlslt_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlslt z0.s, z1.h, z2.h
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslt.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
;
|
|
; FMLSLT (Indexed)
|
|
;
|
|
|
|
define <vscale x 4 x float> @fmlslt_lane_h(<vscale x 4 x float> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
|
|
; CHECK-LABEL: fmlslt_lane_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmlslt z0.s, z1.h, z2.h[3]
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslt.lane.nxv4f32(<vscale x 4 x float> %a,
|
|
<vscale x 8 x half> %b,
|
|
<vscale x 8 x half> %c,
|
|
i32 3)
|
|
ret <vscale x 4 x float> %out
|
|
}
|
|
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlalb.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlalb.lane.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlalt.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlalt.lane.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
|
|
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlslb.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlslb.lane.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlslt.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.fmlslt.lane.nxv4f32(<vscale x 4 x float>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
|