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
146 lines
5.9 KiB
LLVM
146 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfh,+v,+zvfbfmin -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfh,+v,+zvfbfmin -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfhmin,+v,+zvfbfmin -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfhmin,+v,+zvfbfmin -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
define <2 x float> @vfpext_v2f16_v2f32(<2 x half> %a, <2 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2f16_v2f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v9, v8
|
|
; CHECK-NEXT: vmv1r.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x float> @llvm.vp.fpext.v2f32.v2f16(<2 x half> %a, <2 x i1> %m, i32 %vl)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
define <2 x float> @vfpext_v2f16_v2f32_unmasked(<2 x half> %a, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2f16_v2f32_unmasked:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v9, v8
|
|
; CHECK-NEXT: vmv1r.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x float> @llvm.vp.fpext.v2f32.v2f16(<2 x half> %a, <2 x i1> splat (i1 true), i32 %vl)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
define <2 x double> @vfpext_v2f16_v2f64(<2 x half> %a, <2 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2f16_v2f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v9, v8
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x double> @llvm.vp.fpext.v2f64.v2f16(<2 x half> %a, <2 x i1> %m, i32 %vl)
|
|
ret <2 x double> %v
|
|
}
|
|
|
|
define <2 x double> @vfpext_v2f16_v2f64_unmasked(<2 x half> %a, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2f16_v2f64_unmasked:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v9, v8
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x double> @llvm.vp.fpext.v2f64.v2f16(<2 x half> %a, <2 x i1> splat (i1 true), i32 %vl)
|
|
ret <2 x double> %v
|
|
}
|
|
|
|
define <2 x double> @vfpext_v2f32_v2f64(<2 x float> %a, <2 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2f32_v2f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v9, v8
|
|
; CHECK-NEXT: vmv1r.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x double> @llvm.vp.fpext.v2f64.v2f32(<2 x float> %a, <2 x i1> %m, i32 %vl)
|
|
ret <2 x double> %v
|
|
}
|
|
|
|
define <2 x double> @vfpext_v2f32_v2f64_unmasked(<2 x float> %a, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2f32_v2f64_unmasked:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v9, v8
|
|
; CHECK-NEXT: vmv1r.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x double> @llvm.vp.fpext.v2f64.v2f32(<2 x float> %a, <2 x i1> splat (i1 true), i32 %vl)
|
|
ret <2 x double> %v
|
|
}
|
|
|
|
define <15 x double> @vfpext_v15f32_v15f64(<15 x float> %a, <15 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v15f32_v15f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
|
|
; CHECK-NEXT: vmv4r.v v16, v8
|
|
; CHECK-NEXT: vfwcvt.f.f.v v8, v16
|
|
; CHECK-NEXT: ret
|
|
%v = call <15 x double> @llvm.vp.fpext.v15f64.v15f32(<15 x float> %a, <15 x i1> %m, i32 %vl)
|
|
ret <15 x double> %v
|
|
}
|
|
|
|
define <32 x double> @vfpext_v32f32_v32f64(<32 x float> %a, <32 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v32f32_v32f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v24, v8
|
|
; CHECK-NEXT: vsetivli zero, 16, e32, m8, ta, ma
|
|
; CHECK-NEXT: vslidedown.vi v8, v8, 16
|
|
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v16, v8
|
|
; CHECK-NEXT: vmv8r.v v8, v24
|
|
; CHECK-NEXT: ret
|
|
%v = call <32 x double> @llvm.vp.fpext.v32f64.v32f32(<32 x float> %a, <32 x i1> %m, i32 %vl)
|
|
ret <32 x double> %v
|
|
}
|
|
|
|
define <2 x float> @vfpext_v2bf16_v2f32(<2 x bfloat> %a, <2 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2bf16_v2f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v8
|
|
; CHECK-NEXT: vmv1r.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x float> @llvm.vp.fpext.v2f32.v2bf16(<2 x bfloat> %a, <2 x i1> %m, i32 %vl)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
define <2 x float> @vfpext_v2bf16_v2f32_unmasked(<2 x bfloat> %a, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2bf16_v2f32_unmasked:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v8
|
|
; CHECK-NEXT: vmv1r.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x float> @llvm.vp.fpext.v2f32.v2bf16(<2 x bfloat> %a, <2 x i1> shufflevector (<2 x i1> insertelement (<2 x i1> poison, i1 true, i32 0), <2 x i1> poison, <2 x i32> zeroinitializer), i32 %vl)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
define <2 x double> @vfpext_v2bf16_v2f64(<2 x bfloat> %a, <2 x i1> %m, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2bf16_v2f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v8
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x double> @llvm.vp.fpext.v2f64.v2bf16(<2 x bfloat> %a, <2 x i1> %m, i32 %vl)
|
|
ret <2 x double> %v
|
|
}
|
|
|
|
define <2 x double> @vfpext_v2bf16_v2f64_unmasked(<2 x bfloat> %a, i32 zeroext %vl) {
|
|
; CHECK-LABEL: vfpext_v2bf16_v2f64_unmasked:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vfwcvtbf16.f.f.v v9, v8
|
|
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vfwcvt.f.f.v v8, v9
|
|
; CHECK-NEXT: ret
|
|
%v = call <2 x double> @llvm.vp.fpext.v2f64.v2bf16(<2 x bfloat> %a, <2 x i1> shufflevector (<2 x i1> insertelement (<2 x i1> poison, i1 true, i32 0), <2 x i1> poison, <2 x i32> zeroinitializer), i32 %vl)
|
|
ret <2 x double> %v
|
|
}
|