derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/CodeGen/RISCV/rvv/vdot4a.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

338 lines
12 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+zve64x,+experimental-zvdot4a8i \
; RUN: -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+zve64x,+experimental-zvdot4a8i \
; RUN: -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
define <vscale x 1 x i32> @intrinsic_vdot4a_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vv_nxv1i32_nxv1i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, tu, ma
; CHECK-NEXT: vdot4a.vv v8, v9, v10
; CHECK-NEXT: ret
entry:
%a = call <vscale x 1 x i32> @llvm.riscv.vdot4a.nxv1i32.nxv1i32(
<vscale x 1 x i32> %0,
<vscale x 1 x i32> %1,
<vscale x 1 x i32> %2,
iXLen %3, iXLen 0)
ret <vscale x 1 x i32> %a
}
define <vscale x 2 x i32> @intrinsic_vdot4a_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vv_nxv2i32_nxv2i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, m1, tu, ma
; CHECK-NEXT: vdot4a.vv v8, v9, v10
; CHECK-NEXT: ret
entry:
%a = call <vscale x 2 x i32> @llvm.riscv.vdot4a.nxv2i32.nxv2i32(
<vscale x 2 x i32> %0,
<vscale x 2 x i32> %1,
<vscale x 2 x i32> %2,
iXLen %3, iXLen 0)
ret <vscale x 2 x i32> %a
}
define <vscale x 4 x i32> @intrinsic_vdot4a_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vv_nxv4i32_nxv4i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, m2, tu, ma
; CHECK-NEXT: vdot4a.vv v8, v10, v12
; CHECK-NEXT: ret
entry:
%a = call <vscale x 4 x i32> @llvm.riscv.vdot4a.nxv4i32.nxv4i32(
<vscale x 4 x i32> %0,
<vscale x 4 x i32> %1,
<vscale x 4 x i32> %2,
iXLen %3, iXLen 0)
ret <vscale x 4 x i32> %a
}
define <vscale x 8 x i32> @intrinsic_vdot4a_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vv_nxv8i32_nxv8i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, m4, tu, ma
; CHECK-NEXT: vdot4a.vv v8, v12, v16
; CHECK-NEXT: ret
entry:
%a = call <vscale x 8 x i32> @llvm.riscv.vdot4a.nxv8i32.nxv8i32(
<vscale x 8 x i32> %0,
<vscale x 8 x i32> %1,
<vscale x 8 x i32> %2,
iXLen %3, iXLen 0)
ret <vscale x 8 x i32> %a
}
define <vscale x 16 x i32> @intrinsic_vdot4a_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vv_nxv16i32_nxv16i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vl8re32.v v24, (a0)
; CHECK-NEXT: vsetvli zero, a1, e32, m8, tu, ma
; CHECK-NEXT: vdot4a.vv v8, v16, v24
; CHECK-NEXT: ret
entry:
%a = call <vscale x 16 x i32> @llvm.riscv.vdot4a.nxv16i32.nxv16i32(
<vscale x 16 x i32> %0,
<vscale x 16 x i32> %1,
<vscale x 16 x i32> %2,
iXLen %3, iXLen 0)
ret <vscale x 16 x i32> %a
}
define <vscale x 1 x i32> @intrinsic_vdot4a_mask_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vv_nxv1i32_nxv1i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, tu, mu
; CHECK-NEXT: vdot4a.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 1 x i32> @llvm.riscv.vdot4a.mask.nxv1i32.nxv1i32(
<vscale x 1 x i32> %0,
<vscale x 1 x i32> %1,
<vscale x 1 x i32> %2,
<vscale x 1 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 1 x i32> %a
}
define <vscale x 2 x i32> @intrinsic_vdot4a_mask_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vv_nxv2i32_nxv2i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, m1, tu, mu
; CHECK-NEXT: vdot4a.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 2 x i32> @llvm.riscv.vdot4a.mask.nxv2i32.nxv2i32(
<vscale x 2 x i32> %0,
<vscale x 2 x i32> %1,
<vscale x 2 x i32> %2,
<vscale x 2 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 2 x i32> %a
}
define <vscale x 4 x i32> @intrinsic_vdot4a_mask_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vv_nxv4i32_nxv4i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, m2, tu, mu
; CHECK-NEXT: vdot4a.vv v8, v10, v12, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 4 x i32> @llvm.riscv.vdot4a.mask.nxv4i32.nxv4i32(
<vscale x 4 x i32> %0,
<vscale x 4 x i32> %1,
<vscale x 4 x i32> %2,
<vscale x 4 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 4 x i32> %a
}
define <vscale x 8 x i32> @intrinsic_vdot4a_mask_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vv_nxv8i32_nxv8i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a0, e32, m4, tu, mu
; CHECK-NEXT: vdot4a.vv v8, v12, v16, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 8 x i32> @llvm.riscv.vdot4a.mask.nxv8i32.nxv8i32(
<vscale x 8 x i32> %0,
<vscale x 8 x i32> %1,
<vscale x 8 x i32> %2,
<vscale x 8 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 8 x i32> %a
}
define <vscale x 16 x i32> @intrinsic_vdot4a_mask_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, <vscale x 16 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vv_nxv16i32_nxv16i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vl8re32.v v24, (a0)
; CHECK-NEXT: vsetvli zero, a1, e32, m8, tu, mu
; CHECK-NEXT: vdot4a.vv v8, v16, v24, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 16 x i32> @llvm.riscv.vdot4a.mask.nxv16i32.nxv16i32(
<vscale x 16 x i32> %0,
<vscale x 16 x i32> %1,
<vscale x 16 x i32> %2,
<vscale x 16 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 16 x i32> %a
}
define <vscale x 1 x i32> @intrinsic_vdot4a_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vx_nxv1i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, tu, ma
; CHECK-NEXT: vdot4a.vx v8, v9, a0
; CHECK-NEXT: ret
entry:
%a = call <vscale x 1 x i32> @llvm.riscv.vdot4a.nxv1i32.i32(
<vscale x 1 x i32> %0,
<vscale x 1 x i32> %1,
i32 %2,
iXLen %3, iXLen 0)
ret <vscale x 1 x i32> %a
}
define <vscale x 2 x i32> @intrinsic_vdot4a_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vx_nxv2i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m1, tu, ma
; CHECK-NEXT: vdot4a.vx v8, v9, a0
; CHECK-NEXT: ret
entry:
%a = call <vscale x 2 x i32> @llvm.riscv.vdot4a.nxv2i32.i32(
<vscale x 2 x i32> %0,
<vscale x 2 x i32> %1,
i32 %2,
iXLen %3, iXLen 0)
ret <vscale x 2 x i32> %a
}
define <vscale x 4 x i32> @intrinsic_vdot4a_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vx_nxv4i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m2, tu, ma
; CHECK-NEXT: vdot4a.vx v8, v10, a0
; CHECK-NEXT: ret
entry:
%a = call <vscale x 4 x i32> @llvm.riscv.vdot4a.nxv4i32.i32(
<vscale x 4 x i32> %0,
<vscale x 4 x i32> %1,
i32 %2,
iXLen %3, iXLen 0)
ret <vscale x 4 x i32> %a
}
define <vscale x 8 x i32> @intrinsic_vdot4a_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vx_nxv8i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m4, tu, ma
; CHECK-NEXT: vdot4a.vx v8, v12, a0
; CHECK-NEXT: ret
entry:
%a = call <vscale x 8 x i32> @llvm.riscv.vdot4a.nxv8i32.i32(
<vscale x 8 x i32> %0,
<vscale x 8 x i32> %1,
i32 %2,
iXLen %3, iXLen 0)
ret <vscale x 8 x i32> %a
}
define <vscale x 16 x i32> @intrinsic_vdot4a_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_vx_nxv16i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m8, tu, ma
; CHECK-NEXT: vdot4a.vx v8, v16, a0
; CHECK-NEXT: ret
entry:
%a = call <vscale x 16 x i32> @llvm.riscv.vdot4a.nxv16i32.i32(
<vscale x 16 x i32> %0,
<vscale x 16 x i32> %1,
i32 %2,
iXLen %3, iXLen 0)
ret <vscale x 16 x i32> %a
}
define <vscale x 1 x i32> @intrinsic_vdot4a_mask_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vx_nxv1i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, tu, mu
; CHECK-NEXT: vdot4a.vx v8, v9, a0, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 1 x i32> @llvm.riscv.vdot4a.mask.nxv1i32.i32(
<vscale x 1 x i32> %0,
<vscale x 1 x i32> %1,
i32 %2,
<vscale x 1 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 1 x i32> %a
}
define <vscale x 2 x i32> @intrinsic_vdot4a_mask_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vx_nxv2i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m1, tu, mu
; CHECK-NEXT: vdot4a.vx v8, v9, a0, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 2 x i32> @llvm.riscv.vdot4a.mask.nxv2i32.i32(
<vscale x 2 x i32> %0,
<vscale x 2 x i32> %1,
i32 %2,
<vscale x 2 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 2 x i32> %a
}
define <vscale x 4 x i32> @intrinsic_vdot4a_mask_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vx_nxv4i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m2, tu, mu
; CHECK-NEXT: vdot4a.vx v8, v10, a0, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 4 x i32> @llvm.riscv.vdot4a.mask.nxv4i32.i32(
<vscale x 4 x i32> %0,
<vscale x 4 x i32> %1,
i32 %2,
<vscale x 4 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 4 x i32> %a
}
define <vscale x 8 x i32> @intrinsic_vdot4a_mask_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vx_nxv8i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m4, tu, mu
; CHECK-NEXT: vdot4a.vx v8, v12, a0, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 8 x i32> @llvm.riscv.vdot4a.mask.nxv8i32.i32(
<vscale x 8 x i32> %0,
<vscale x 8 x i32> %1,
i32 %2,
<vscale x 8 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 8 x i32> %a
}
define <vscale x 16 x i32> @intrinsic_vdot4a_mask_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vdot4a_mask_vx_nxv16i32_i32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetvli zero, a1, e32, m8, tu, mu
; CHECK-NEXT: vdot4a.vx v8, v16, a0, v0.t
; CHECK-NEXT: ret
entry:
%a = call <vscale x 16 x i32> @llvm.riscv.vdot4a.mask.nxv16i32.i32(
<vscale x 16 x i32> %0,
<vscale x 16 x i32> %1,
i32 %2,
<vscale x 16 x i1> %m,
iXLen %3, iXLen 0)
ret <vscale x 16 x i32> %a
}
Reference in new issue View Git Blame Copy Permalink