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
248 lines
10 KiB
LLVM
248 lines
10 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,V
|
|
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,V
|
|
; RUN: llc -mtriple=riscv32 -mattr=+zve32x,+zvl128b -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVE32
|
|
; RUN: llc -mtriple=riscv64 -mattr=+zve32x,+zvl128b -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVE32
|
|
|
|
define <vscale x 1 x i8> @masked_load_nxv1i8(ptr %a, <vscale x 1 x i1> %mask) nounwind {
|
|
; V-LABEL: masked_load_nxv1i8:
|
|
; V: # %bb.0:
|
|
; V-NEXT: vsetvli a1, zero, e8, mf8, ta, ma
|
|
; V-NEXT: vle8.v v8, (a0), v0.t
|
|
; V-NEXT: ret
|
|
;
|
|
; ZVE32-LABEL: masked_load_nxv1i8:
|
|
; ZVE32: # %bb.0:
|
|
; ZVE32-NEXT: csrr a1, vlenb
|
|
; ZVE32-NEXT: srli a1, a1, 3
|
|
; ZVE32-NEXT: vsetvli zero, a1, e8, mf4, ta, ma
|
|
; ZVE32-NEXT: vle8.v v8, (a0), v0.t
|
|
; ZVE32-NEXT: ret
|
|
%load = call <vscale x 1 x i8> @llvm.masked.load.nxv1i8(ptr %a, i32 1, <vscale x 1 x i1> %mask, <vscale x 1 x i8> poison)
|
|
ret <vscale x 1 x i8> %load
|
|
}
|
|
|
|
define <vscale x 1 x i8> @masked_load_passthru_nxv1i8(ptr %a, <vscale x 1 x i1> %mask) nounwind {
|
|
; V-LABEL: masked_load_passthru_nxv1i8:
|
|
; V: # %bb.0:
|
|
; V-NEXT: vsetvli a1, zero, e8, mf8, ta, mu
|
|
; V-NEXT: vmv.v.i v8, 0
|
|
; V-NEXT: vle8.v v8, (a0), v0.t
|
|
; V-NEXT: ret
|
|
;
|
|
; ZVE32-LABEL: masked_load_passthru_nxv1i8:
|
|
; ZVE32: # %bb.0:
|
|
; ZVE32-NEXT: csrr a1, vlenb
|
|
; ZVE32-NEXT: srli a1, a1, 3
|
|
; ZVE32-NEXT: vsetvli zero, a1, e8, mf4, ta, mu
|
|
; ZVE32-NEXT: vmv.v.i v8, 0
|
|
; ZVE32-NEXT: vle8.v v8, (a0), v0.t
|
|
; ZVE32-NEXT: ret
|
|
%load = call <vscale x 1 x i8> @llvm.masked.load.nxv1i8(ptr %a, i32 1, <vscale x 1 x i1> %mask, <vscale x 1 x i8> zeroinitializer)
|
|
ret <vscale x 1 x i8> %load
|
|
}
|
|
|
|
define <vscale x 1 x i16> @masked_load_nxv1i16(ptr %a, <vscale x 1 x i1> %mask) nounwind {
|
|
; V-LABEL: masked_load_nxv1i16:
|
|
; V: # %bb.0:
|
|
; V-NEXT: vsetvli a1, zero, e16, mf4, ta, ma
|
|
; V-NEXT: vle16.v v8, (a0), v0.t
|
|
; V-NEXT: ret
|
|
;
|
|
; ZVE32-LABEL: masked_load_nxv1i16:
|
|
; ZVE32: # %bb.0:
|
|
; ZVE32-NEXT: csrr a1, vlenb
|
|
; ZVE32-NEXT: srli a1, a1, 3
|
|
; ZVE32-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; ZVE32-NEXT: vle16.v v8, (a0), v0.t
|
|
; ZVE32-NEXT: ret
|
|
%load = call <vscale x 1 x i16> @llvm.masked.load.nxv1i16(ptr %a, i32 2, <vscale x 1 x i1> %mask, <vscale x 1 x i16> poison)
|
|
ret <vscale x 1 x i16> %load
|
|
}
|
|
|
|
define <vscale x 1 x i32> @masked_load_nxv1i32(ptr %a, <vscale x 1 x i1> %mask) nounwind {
|
|
; V-LABEL: masked_load_nxv1i32:
|
|
; V: # %bb.0:
|
|
; V-NEXT: vsetvli a1, zero, e32, mf2, ta, ma
|
|
; V-NEXT: vle32.v v8, (a0), v0.t
|
|
; V-NEXT: ret
|
|
;
|
|
; ZVE32-LABEL: masked_load_nxv1i32:
|
|
; ZVE32: # %bb.0:
|
|
; ZVE32-NEXT: csrr a1, vlenb
|
|
; ZVE32-NEXT: srli a1, a1, 3
|
|
; ZVE32-NEXT: vsetvli zero, a1, e32, m1, ta, ma
|
|
; ZVE32-NEXT: vle32.v v8, (a0), v0.t
|
|
; ZVE32-NEXT: ret
|
|
%load = call <vscale x 1 x i32> @llvm.masked.load.nxv1i32(ptr %a, i32 4, <vscale x 1 x i1> %mask, <vscale x 1 x i32> poison)
|
|
ret <vscale x 1 x i32> %load
|
|
}
|
|
|
|
define <vscale x 2 x i8> @masked_load_nxv2i8(ptr %a, <vscale x 2 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv2i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, mf4, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8(ptr %a, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> poison)
|
|
ret <vscale x 2 x i8> %load
|
|
}
|
|
|
|
define <vscale x 2 x i16> @masked_load_nxv2i16(ptr %a, <vscale x 2 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv2i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16(ptr %a, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> poison)
|
|
ret <vscale x 2 x i16> %load
|
|
}
|
|
|
|
define <vscale x 2 x i32> @masked_load_nxv2i32(ptr %a, <vscale x 2 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv2i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e32, m1, ta, ma
|
|
; CHECK-NEXT: vle32.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32(ptr %a, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> poison)
|
|
ret <vscale x 2 x i32> %load
|
|
}
|
|
|
|
define <vscale x 4 x i8> @masked_load_nxv4i8(ptr %a, <vscale x 4 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv4i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, mf2, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8(ptr %a, i32 1, <vscale x 4 x i1> %mask, <vscale x 4 x i8> poison)
|
|
ret <vscale x 4 x i8> %load
|
|
}
|
|
|
|
define <vscale x 4 x i16> @masked_load_nxv4i16(ptr %a, <vscale x 4 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv4i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16(ptr %a, i32 2, <vscale x 4 x i1> %mask, <vscale x 4 x i16> poison)
|
|
ret <vscale x 4 x i16> %load
|
|
}
|
|
|
|
define <vscale x 4 x i32> @masked_load_nxv4i32(ptr %a, <vscale x 4 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv4i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, ma
|
|
; CHECK-NEXT: vle32.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32(ptr %a, i32 4, <vscale x 4 x i1> %mask, <vscale x 4 x i32> poison)
|
|
ret <vscale x 4 x i32> %load
|
|
}
|
|
|
|
define <vscale x 8 x i8> @masked_load_nxv8i8(ptr %a, <vscale x 8 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv8i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, m1, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8(ptr %a, i32 1, <vscale x 8 x i1> %mask, <vscale x 8 x i8> poison)
|
|
ret <vscale x 8 x i8> %load
|
|
}
|
|
|
|
define <vscale x 8 x i16> @masked_load_nxv8i16(ptr %a, <vscale x 8 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv8i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16(ptr %a, i32 2, <vscale x 8 x i1> %mask, <vscale x 8 x i16> poison)
|
|
ret <vscale x 8 x i16> %load
|
|
}
|
|
|
|
define <vscale x 8 x i32> @masked_load_nxv8i32(ptr %a, <vscale x 8 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv8i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e32, m4, ta, ma
|
|
; CHECK-NEXT: vle32.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 8 x i32> @llvm.masked.load.nxv8i32(ptr %a, i32 4, <vscale x 8 x i1> %mask, <vscale x 8 x i32> poison)
|
|
ret <vscale x 8 x i32> %load
|
|
}
|
|
|
|
define <vscale x 16 x i8> @masked_load_nxv16i8(ptr %a, <vscale x 16 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv16i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, m2, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8(ptr %a, i32 1, <vscale x 16 x i1> %mask, <vscale x 16 x i8> poison)
|
|
ret <vscale x 16 x i8> %load
|
|
}
|
|
|
|
define <vscale x 16 x i16> @masked_load_nxv16i16(ptr %a, <vscale x 16 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv16i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 16 x i16> @llvm.masked.load.nxv16i16(ptr %a, i32 2, <vscale x 16 x i1> %mask, <vscale x 16 x i16> poison)
|
|
ret <vscale x 16 x i16> %load
|
|
}
|
|
|
|
define <vscale x 16 x i32> @masked_load_nxv16i32(ptr %a, <vscale x 16 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv16i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e32, m8, ta, ma
|
|
; CHECK-NEXT: vle32.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 16 x i32> @llvm.masked.load.nxv16i32(ptr %a, i32 4, <vscale x 16 x i1> %mask, <vscale x 16 x i32> poison)
|
|
ret <vscale x 16 x i32> %load
|
|
}
|
|
|
|
define <vscale x 32 x i8> @masked_load_nxv32i8(ptr %a, <vscale x 32 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv32i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, m4, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 32 x i8> @llvm.masked.load.nxv32i8(ptr %a, i32 1, <vscale x 32 x i1> %mask, <vscale x 32 x i8> poison)
|
|
ret <vscale x 32 x i8> %load
|
|
}
|
|
|
|
define <vscale x 32 x i16> @masked_load_nxv32i16(ptr %a, <vscale x 32 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv32i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 32 x i16> @llvm.masked.load.nxv32i16(ptr %a, i32 2, <vscale x 32 x i1> %mask, <vscale x 32 x i16> poison)
|
|
ret <vscale x 32 x i16> %load
|
|
}
|
|
|
|
define <vscale x 64 x i8> @masked_load_nxv64i8(ptr %a, <vscale x 64 x i1> %mask) nounwind {
|
|
; CHECK-LABEL: masked_load_nxv64i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, m8, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0), v0.t
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 64 x i8> @llvm.masked.load.nxv64i8(ptr %a, i32 1, <vscale x 64 x i1> %mask, <vscale x 64 x i8> poison)
|
|
ret <vscale x 64 x i8> %load
|
|
}
|
|
|
|
define <vscale x 2 x i8> @masked_load_zero_mask(ptr %a) nounwind {
|
|
; CHECK-LABEL: masked_load_zero_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8(ptr %a, i32 1, <vscale x 2 x i1> zeroinitializer, <vscale x 2 x i8> poison)
|
|
ret <vscale x 2 x i8> %load
|
|
}
|
|
|
|
define <vscale x 2 x i8> @masked_load_allones_mask(ptr %a, <vscale x 2 x i8> %maskedoff) nounwind {
|
|
; CHECK-LABEL: masked_load_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli a1, zero, e8, mf4, ta, ma
|
|
; CHECK-NEXT: vle8.v v8, (a0)
|
|
; CHECK-NEXT: ret
|
|
%load = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8(ptr %a, i32 1, <vscale x 2 x i1> splat (i1 1), <vscale x 2 x i8> %maskedoff)
|
|
ret <vscale x 2 x i8> %load
|
|
}
|