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
117 lines
5.2 KiB
LLVM
117 lines
5.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: llc -mattr=+sve2 < %s | FileCheck %s
|
|
; RUN: llc -mattr=+sve,+sme2 < %s | FileCheck %s
|
|
; RUN: llc -mattr=+sme2 -force-streaming < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-linux"
|
|
|
|
define <vscale x 8 x half> @famin_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
|
|
; CHECK-LABEL: famin_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famin.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
|
|
ret <vscale x 8 x half> %r
|
|
}
|
|
|
|
define <vscale x 4 x float> @famin_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
|
|
; CHECK-LABEL: famin_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin z0.s, p0/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famin.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
|
|
ret <vscale x 4 x float> %r
|
|
}
|
|
|
|
define <vscale x 2 x double> @famin_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
|
|
; CHECK-LABEL: famin_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famin.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
|
|
ret <vscale x 2 x double> %r
|
|
}
|
|
|
|
define <vscale x 8 x half> @famin_u_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
|
|
; CHECK-LABEL: famin_u_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famin.u.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %b, <vscale x 8 x half> %a)
|
|
ret <vscale x 8 x half> %r
|
|
}
|
|
|
|
define <vscale x 4 x float> @famin_u_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
|
|
; CHECK-LABEL: famin_u_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin z0.s, p0/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famin.u.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %b, <vscale x 4 x float> %a)
|
|
ret <vscale x 4 x float> %r
|
|
}
|
|
|
|
define <vscale x 2 x double> @famin_u_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
|
|
; CHECK-LABEL: famin_u_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famin.u.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %b, <vscale x 2 x double> %a)
|
|
ret <vscale x 2 x double> %r
|
|
}
|
|
|
|
define <vscale x 8 x half> @famax_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
|
|
; CHECK-LABEL: famax_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famax.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
|
|
ret <vscale x 8 x half> %r
|
|
}
|
|
|
|
define <vscale x 4 x float> @famax_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
|
|
; CHECK-LABEL: famax_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax z0.s, p0/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famax.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
|
|
ret <vscale x 4 x float> %r
|
|
}
|
|
|
|
define <vscale x 2 x double> @famax_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
|
|
; CHECK-LABEL: famax_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famax.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
|
|
ret <vscale x 2 x double> %r
|
|
}
|
|
|
|
define <vscale x 8 x half> @famax_u_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
|
|
; CHECK-LABEL: famax_u_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famax.u.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %b, <vscale x 8 x half> %a)
|
|
ret <vscale x 8 x half> %r
|
|
}
|
|
|
|
define <vscale x 4 x float> @famax_u_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
|
|
; CHECK-LABEL: famax_u_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax z0.s, p0/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famax.u.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %b, <vscale x 4 x float> %a)
|
|
ret <vscale x 4 x float> %r
|
|
}
|
|
|
|
define <vscale x 2 x double> @famax_u_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
|
|
; CHECK-LABEL: famax_u_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famax.u.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %b, <vscale x 2 x double> %a)
|
|
ret <vscale x 2 x double> %r
|
|
}
|
|
|
|
attributes #0 = { nounwind "target-features" = "+faminmax" }
|