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
217 lines
7.5 KiB
LLVM
217 lines
7.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvfbfa \
|
|
; RUN: -verify-machineinstrs -target-abi=ilp32d | FileCheck %s
|
|
; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvfbfa \
|
|
; RUN: -verify-machineinstrs -target-abi=lp64d | FileCheck %s
|
|
|
|
define <vscale x 1 x bfloat> @intrinsic_vfrec7_v_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, iXLen %1) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_v_nxv1bf16_nxv1bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, mf4, ta, ma
|
|
; CHECK-NEXT: vfrec7.v v8, v8
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 1 x bfloat> @llvm.riscv.vfrec7.nxv1bf16(
|
|
<vscale x 1 x bfloat> poison,
|
|
<vscale x 1 x bfloat> %0,
|
|
iXLen 0, iXLen %1)
|
|
|
|
ret <vscale x 1 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 1 x bfloat> @intrinsic_vfrec7_mask_v_nxv1bf16_nxv1bf16(<vscale x 1 x i1> %0, <vscale x 1 x bfloat> %1, <vscale x 1 x bfloat> %2, iXLen %3) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_mask_v_nxv1bf16_nxv1bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, mf4, ta, mu
|
|
; CHECK-NEXT: vfrec7.v v8, v9, v0.t
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 1 x bfloat> @llvm.riscv.vfrec7.mask.nxv1bf16(
|
|
<vscale x 1 x bfloat> %1,
|
|
<vscale x 1 x bfloat> %2,
|
|
<vscale x 1 x i1> %0,
|
|
iXLen 0, iXLen %3, iXLen 1)
|
|
|
|
ret <vscale x 1 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 2 x bfloat> @intrinsic_vfrec7_v_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, iXLen %1) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_v_nxv2bf16_nxv2bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, mf2, ta, ma
|
|
; CHECK-NEXT: vfrec7.v v8, v8
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 2 x bfloat> @llvm.riscv.vfrec7.nxv2bf16(
|
|
<vscale x 2 x bfloat> poison,
|
|
<vscale x 2 x bfloat> %0,
|
|
iXLen 0, iXLen %1)
|
|
|
|
ret <vscale x 2 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 2 x bfloat> @intrinsic_vfrec7_mask_v_nxv2bf16_nxv2bf16(<vscale x 2 x i1> %0, <vscale x 2 x bfloat> %1, <vscale x 2 x bfloat> %2, iXLen %3) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_mask_v_nxv2bf16_nxv2bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, mf2, ta, mu
|
|
; CHECK-NEXT: vfrec7.v v8, v9, v0.t
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 2 x bfloat> @llvm.riscv.vfrec7.mask.nxv2bf16(
|
|
<vscale x 2 x bfloat> %1,
|
|
<vscale x 2 x bfloat> %2,
|
|
<vscale x 2 x i1> %0,
|
|
iXLen 0, iXLen %3, iXLen 1)
|
|
|
|
ret <vscale x 2 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 4 x bfloat> @intrinsic_vfrec7_v_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, iXLen %1) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_v_nxv4bf16_nxv4bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m1, ta, ma
|
|
; CHECK-NEXT: vfrec7.v v8, v8
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 4 x bfloat> @llvm.riscv.vfrec7.nxv4bf16(
|
|
<vscale x 4 x bfloat> poison,
|
|
<vscale x 4 x bfloat> %0,
|
|
iXLen 0, iXLen %1)
|
|
|
|
ret <vscale x 4 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 4 x bfloat> @intrinsic_vfrec7_mask_v_nxv4bf16_nxv4bf16(<vscale x 4 x i1> %0, <vscale x 4 x bfloat> %1, <vscale x 4 x bfloat> %2, iXLen %3) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_mask_v_nxv4bf16_nxv4bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m1, ta, mu
|
|
; CHECK-NEXT: vfrec7.v v8, v9, v0.t
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 4 x bfloat> @llvm.riscv.vfrec7.mask.nxv4bf16(
|
|
<vscale x 4 x bfloat> %1,
|
|
<vscale x 4 x bfloat> %2,
|
|
<vscale x 4 x i1> %0,
|
|
iXLen 0, iXLen %3, iXLen 1)
|
|
|
|
ret <vscale x 4 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @intrinsic_vfrec7_v_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, iXLen %1) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_v_nxv8bf16_nxv8bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m2, ta, ma
|
|
; CHECK-NEXT: vfrec7.v v8, v8
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 8 x bfloat> @llvm.riscv.vfrec7.nxv8bf16(
|
|
<vscale x 8 x bfloat> poison,
|
|
<vscale x 8 x bfloat> %0,
|
|
iXLen 0, iXLen %1)
|
|
|
|
ret <vscale x 8 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @intrinsic_vfrec7_mask_v_nxv8bf16_nxv8bf16(<vscale x 8 x i1> %0, <vscale x 8 x bfloat> %1, <vscale x 8 x bfloat> %2, iXLen %3) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_mask_v_nxv8bf16_nxv8bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m2, ta, mu
|
|
; CHECK-NEXT: vfrec7.v v8, v10, v0.t
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 8 x bfloat> @llvm.riscv.vfrec7.mask.nxv8bf16(
|
|
<vscale x 8 x bfloat> %1,
|
|
<vscale x 8 x bfloat> %2,
|
|
<vscale x 8 x i1> %0,
|
|
iXLen 0, iXLen %3, iXLen 1)
|
|
|
|
ret <vscale x 8 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 16 x bfloat> @intrinsic_vfrec7_v_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, iXLen %1) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_v_nxv16bf16_nxv16bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m4, ta, ma
|
|
; CHECK-NEXT: vfrec7.v v8, v8
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 16 x bfloat> @llvm.riscv.vfrec7.nxv16bf16(
|
|
<vscale x 16 x bfloat> poison,
|
|
<vscale x 16 x bfloat> %0,
|
|
iXLen 0, iXLen %1)
|
|
|
|
ret <vscale x 16 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 16 x bfloat> @intrinsic_vfrec7_mask_v_nxv16bf16_nxv16bf16(<vscale x 16 x i1> %0, <vscale x 16 x bfloat> %1, <vscale x 16 x bfloat> %2, iXLen %3) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_mask_v_nxv16bf16_nxv16bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m4, ta, mu
|
|
; CHECK-NEXT: vfrec7.v v8, v12, v0.t
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 16 x bfloat> @llvm.riscv.vfrec7.mask.nxv16bf16(
|
|
<vscale x 16 x bfloat> %1,
|
|
<vscale x 16 x bfloat> %2,
|
|
<vscale x 16 x i1> %0,
|
|
iXLen 0, iXLen %3, iXLen 1)
|
|
|
|
ret <vscale x 16 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 32 x bfloat> @intrinsic_vfrec7_v_nxv32bf16_nxv32bf16(<vscale x 32 x bfloat> %0, iXLen %1) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_v_nxv32bf16_nxv32bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m8, ta, ma
|
|
; CHECK-NEXT: vfrec7.v v8, v8
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 32 x bfloat> @llvm.riscv.vfrec7.nxv32bf16(
|
|
<vscale x 32 x bfloat> poison,
|
|
<vscale x 32 x bfloat> %0,
|
|
iXLen 0, iXLen %1)
|
|
|
|
ret <vscale x 32 x bfloat> %a
|
|
}
|
|
|
|
define <vscale x 32 x bfloat> @intrinsic_vfrec7_mask_v_nxv32bf16_nxv32bf16(<vscale x 32 x i1> %0, <vscale x 32 x bfloat> %1, <vscale x 32 x bfloat> %2, iXLen %3) nounwind {
|
|
; CHECK-LABEL: intrinsic_vfrec7_mask_v_nxv32bf16_nxv32bf16:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: fsrmi a1, 0
|
|
; CHECK-NEXT: vsetvli zero, a0, e16alt, m8, ta, mu
|
|
; CHECK-NEXT: vfrec7.v v8, v16, v0.t
|
|
; CHECK-NEXT: fsrm a1
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a = call <vscale x 32 x bfloat> @llvm.riscv.vfrec7.mask.nxv32bf16(
|
|
<vscale x 32 x bfloat> %1,
|
|
<vscale x 32 x bfloat> %2,
|
|
<vscale x 32 x i1> %0,
|
|
iXLen 0, iXLen %3, iXLen 1)
|
|
|
|
ret <vscale x 32 x bfloat> %a
|
|
}
|
|
|