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
187 lines
7.0 KiB
LLVM
187 lines
7.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+v,+zfbfmin,+zvfbfmin -target-abi=ilp32d \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFBFMIN
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+v,+zfbfmin,+zvfbfmin -target-abi=lp64d \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFBFMIN
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+v,+zfbfmin,+experimental-zvfbfa \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFBFA
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+v,+zfbfmin,+experimental-zvfbfa \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFBFA
|
|
|
|
define <2 x bfloat> @select_v2bf16(i1 zeroext %c, <2 x bfloat> %a, <2 x bfloat> %b) {
|
|
; CHECK-LABEL: select_v2bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v10, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v10, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%v = select i1 %c, <2 x bfloat> %a, <2 x bfloat> %b
|
|
ret <2 x bfloat> %v
|
|
}
|
|
|
|
define <2 x bfloat> @selectcc_v2bf16(bfloat %a, bfloat %b, <2 x bfloat> %c, <2 x bfloat> %d) {
|
|
; CHECK-LABEL: selectcc_v2bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: feq.s a0, fa4, fa5
|
|
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v10, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v10, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%cmp = fcmp oeq bfloat %a, %b
|
|
%v = select i1 %cmp, <2 x bfloat> %c, <2 x bfloat> %d
|
|
ret <2 x bfloat> %v
|
|
}
|
|
|
|
define <4 x bfloat> @select_v4bf16(i1 zeroext %c, <4 x bfloat> %a, <4 x bfloat> %b) {
|
|
; CHECK-LABEL: select_v4bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v10, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v10, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%v = select i1 %c, <4 x bfloat> %a, <4 x bfloat> %b
|
|
ret <4 x bfloat> %v
|
|
}
|
|
|
|
define <4 x bfloat> @selectcc_v4bf16(bfloat %a, bfloat %b, <4 x bfloat> %c, <4 x bfloat> %d) {
|
|
; CHECK-LABEL: selectcc_v4bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: feq.s a0, fa4, fa5
|
|
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v10, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v10, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%cmp = fcmp oeq bfloat %a, %b
|
|
%v = select i1 %cmp, <4 x bfloat> %c, <4 x bfloat> %d
|
|
ret <4 x bfloat> %v
|
|
}
|
|
|
|
define <8 x bfloat> @select_v8bf16(i1 zeroext %c, <8 x bfloat> %a, <8 x bfloat> %b) {
|
|
; CHECK-LABEL: select_v8bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v10, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v10, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%v = select i1 %c, <8 x bfloat> %a, <8 x bfloat> %b
|
|
ret <8 x bfloat> %v
|
|
}
|
|
|
|
define <8 x bfloat> @selectcc_v8bf16(bfloat %a, bfloat %b, <8 x bfloat> %c, <8 x bfloat> %d) {
|
|
; CHECK-LABEL: selectcc_v8bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: feq.s a0, fa4, fa5
|
|
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v10, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v10, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%cmp = fcmp oeq bfloat %a, %b
|
|
%v = select i1 %cmp, <8 x bfloat> %c, <8 x bfloat> %d
|
|
ret <8 x bfloat> %v
|
|
}
|
|
|
|
define <16 x bfloat> @select_v16bf16(i1 zeroext %c, <16 x bfloat> %a, <16 x bfloat> %b) {
|
|
; CHECK-LABEL: select_v16bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v12, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v12, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v10, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%v = select i1 %c, <16 x bfloat> %a, <16 x bfloat> %b
|
|
ret <16 x bfloat> %v
|
|
}
|
|
|
|
define <16 x bfloat> @selectcc_v16bf16(bfloat %a, bfloat %b, <16 x bfloat> %c, <16 x bfloat> %d) {
|
|
; CHECK-LABEL: selectcc_v16bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: feq.s a0, fa4, fa5
|
|
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
|
|
; CHECK-NEXT: vmv.v.x v12, a0
|
|
; CHECK-NEXT: vmsne.vi v0, v12, 0
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vmerge.vvm v8, v10, v8, v0
|
|
; CHECK-NEXT: ret
|
|
%cmp = fcmp oeq bfloat %a, %b
|
|
%v = select i1 %cmp, <16 x bfloat> %c, <16 x bfloat> %d
|
|
ret <16 x bfloat> %v
|
|
}
|
|
|
|
define <8 x bfloat> @vselect_vf_v8bf16(bfloat %a, <8 x bfloat> %vb, <8 x i1> %cc) {
|
|
; ZVFBFMIN-LABEL: vselect_vf_v8bf16:
|
|
; ZVFBFMIN: # %bb.0:
|
|
; ZVFBFMIN-NEXT: fmv.x.h a0, fa0
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 8, e16, m1, ta, ma
|
|
; ZVFBFMIN-NEXT: vmv.v.x v9, a0
|
|
; ZVFBFMIN-NEXT: vmerge.vvm v8, v8, v9, v0
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: vselect_vf_v8bf16:
|
|
; ZVFBFA: # %bb.0:
|
|
; ZVFBFA-NEXT: vsetivli zero, 8, e16alt, m1, ta, ma
|
|
; ZVFBFA-NEXT: vfmerge.vfm v8, v8, fa0, v0
|
|
; ZVFBFA-NEXT: ret
|
|
%insert = insertelement <8 x bfloat> poison, bfloat %a, i32 0
|
|
%va = shufflevector <8 x bfloat> %insert, <8 x bfloat> poison, <8 x i32> zeroinitializer
|
|
%vsel = select <8 x i1> %cc, <8 x bfloat> %va, <8 x bfloat> %vb
|
|
ret <8 x bfloat> %vsel
|
|
}
|
|
|
|
define <16 x bfloat> @vselect_vf_v16bf16(bfloat %a, <16 x bfloat> %vb, <16 x i1> %cc) {
|
|
; ZVFBFMIN-LABEL: vselect_vf_v16bf16:
|
|
; ZVFBFMIN: # %bb.0:
|
|
; ZVFBFMIN-NEXT: fmv.x.h a0, fa0
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 16, e16, m2, ta, ma
|
|
; ZVFBFMIN-NEXT: vmv.v.x v10, a0
|
|
; ZVFBFMIN-NEXT: vmerge.vvm v8, v8, v10, v0
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: vselect_vf_v16bf16:
|
|
; ZVFBFA: # %bb.0:
|
|
; ZVFBFA-NEXT: vsetivli zero, 16, e16alt, m2, ta, ma
|
|
; ZVFBFA-NEXT: vfmerge.vfm v8, v8, fa0, v0
|
|
; ZVFBFA-NEXT: ret
|
|
%insert = insertelement <16 x bfloat> poison, bfloat %a, i32 0
|
|
%va = shufflevector <16 x bfloat> %insert, <16 x bfloat> poison, <16 x i32> zeroinitializer
|
|
%vsel = select <16 x i1> %cc, <16 x bfloat> %va, <16 x bfloat> %vb
|
|
ret <16 x bfloat> %vsel
|
|
}
|
|
|
|
define <8 x bfloat> @vselect_vfpzero_v8bf16(<8 x bfloat> %vb, <8 x i1> %cc) {
|
|
; ZVFBFMIN-LABEL: vselect_vfpzero_v8bf16:
|
|
; ZVFBFMIN: # %bb.0:
|
|
; ZVFBFMIN-NEXT: vsetivli zero, 8, e16, m1, ta, ma
|
|
; ZVFBFMIN-NEXT: vmv.v.i v9, 0
|
|
; ZVFBFMIN-NEXT: vmerge.vvm v8, v8, v9, v0
|
|
; ZVFBFMIN-NEXT: ret
|
|
;
|
|
; ZVFBFA-LABEL: vselect_vfpzero_v8bf16:
|
|
; ZVFBFA: # %bb.0:
|
|
; ZVFBFA-NEXT: vsetivli zero, 8, e16, m1, ta, ma
|
|
; ZVFBFA-NEXT: vmerge.vim v8, v8, 0, v0
|
|
; ZVFBFA-NEXT: ret
|
|
%vsel = select <8 x i1> %cc, <8 x bfloat> splat (bfloat 0.0), <8 x bfloat> %vb
|
|
ret <8 x bfloat> %vsel
|
|
}
|