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
1009 lines
42 KiB
LLVM
1009 lines
42 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfh,+zvfbfmin,+v \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfh,+zvfbfmin,+v \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfhmin,+zvfbfmin,+v \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s
|
|
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfhmin,+zvfbfmin,+v \
|
|
; RUN: -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
define { <vscale x 1 x i8>, i32 } @vploadff_nxv1i8(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf8, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i8>, i32 } @llvm.vp.load.ff.nxv1i8.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x i8>, i32 } @vploadff_nxv1i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf8, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i8>, i32 } @llvm.vp.load.ff.nxv1i8.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i8>, i32 } @vploadff_nxv2i8(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf4, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i8>, i32 } @llvm.vp.load.ff.nxv2i8.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i8>, i32 } @vploadff_nxv2i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf4, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i8>, i32 } @llvm.vp.load.ff.nxv2i8.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i8>, i32 } @vploadff_nxv4i8(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i8>, i32 } @llvm.vp.load.ff.nxv4i8.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i8>, i32 } @vploadff_nxv4i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i8>, i32 } @llvm.vp.load.ff.nxv4i8.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i8>, i32 } @vploadff_nxv8i8(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m1, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i8>, i32 } @llvm.vp.load.ff.nxv8i8.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i8>, i32 } @vploadff_nxv8i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m1, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i8>, i32 } @llvm.vp.load.ff.nxv8i8.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x i8>, i32 } @vploadff_nxv16i8(ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x i8>, i32 } @llvm.vp.load.ff.nxv16i8.p0(ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
|
|
ret { <vscale x 16 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x i8>, i32 } @vploadff_nxv16i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x i8>, i32 } @llvm.vp.load.ff.nxv16i8.p0(ptr %ptr, <vscale x 16 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 16 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x i8>, i32 } @vploadff_nxv32i8(ptr %ptr, <vscale x 32 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m4, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x i8>, i32 } @llvm.vp.load.ff.nxv32i8.p0(ptr %ptr, <vscale x 32 x i1> %m, i32 %evl)
|
|
ret { <vscale x 32 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x i8>, i32 } @vploadff_nxv32i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m4, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x i8>, i32 } @llvm.vp.load.ff.nxv32i8.p0(ptr %ptr, <vscale x 32 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 32 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 64 x i8>, i32 } @vploadff_nxv64i8(ptr %ptr, <vscale x 64 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv64i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m8, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 64 x i8>, i32 } @llvm.vp.load.ff.nxv64i8.p0(ptr %ptr, <vscale x 64 x i1> %m, i32 %evl)
|
|
ret { <vscale x 64 x i8>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 64 x i8>, i32 } @vploadff_nxv64i8_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv64i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, m8, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 64 x i8>, i32 } @llvm.vp.load.ff.nxv64i8.p0(ptr %ptr, <vscale x 64 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 64 x i8>, i32 } %load
|
|
}
|
|
|
|
define <vscale x 128 x i8> @vploadff_nxv128i8(ptr %ptr, ptr %evl_out, <vscale x 128 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv128i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: csrr a3, vlenb
|
|
; CHECK-NEXT: slli a3, a3, 3
|
|
; CHECK-NEXT: bltu a2, a3, .LBB14_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: mv a2, a3
|
|
; CHECK-NEXT: .LBB14_2:
|
|
; CHECK-NEXT: vsetvli zero, a2, e8, m8, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: sw a0, 0(a1)
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 128 x i8>, i32 } @llvm.vp.load.ff.nxv128i8.p0(ptr %ptr, <vscale x 128 x i1> %m, i32 %evl)
|
|
%result0 = extractvalue { <vscale x 128 x i8>, i32 } %load, 0
|
|
%result1 = extractvalue { <vscale x 128 x i8>, i32 } %load, 1
|
|
store i32 %result1, ptr %evl_out
|
|
ret <vscale x 128 x i8> %result0
|
|
}
|
|
|
|
define <vscale x 128 x i8> @vploadff_nxv128i8_allones_mask(ptr %ptr, ptr %evl_out, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv128i8_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: csrr a3, vlenb
|
|
; CHECK-NEXT: slli a3, a3, 3
|
|
; CHECK-NEXT: bltu a2, a3, .LBB15_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: mv a2, a3
|
|
; CHECK-NEXT: .LBB15_2:
|
|
; CHECK-NEXT: vsetvli zero, a2, e8, m8, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: sw a0, 0(a1)
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 128 x i8>, i32 } @llvm.vp.load.ff.nxv128i8.p0(ptr %ptr, <vscale x 128 x i1> splat (i1 true), i32 %evl)
|
|
%result0 = extractvalue { <vscale x 128 x i8>, i32 } %load, 0
|
|
%result1 = extractvalue { <vscale x 128 x i8>, i32 } %load, 1
|
|
store i32 %result1, ptr %evl_out
|
|
ret <vscale x 128 x i8> %result0
|
|
}
|
|
|
|
define { <vscale x 1 x i16>, i32 } @vploadff_nxv1i16(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i16>, i32 } @llvm.vp.load.ff.nxv1i16.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x i16>, i32 } @vploadff_nxv1i16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i16>, i32 } @llvm.vp.load.ff.nxv1i16.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i16>, i32 } @vploadff_nxv2i16(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i16>, i32 } @llvm.vp.load.ff.nxv2i16.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i16>, i32 } @vploadff_nxv2i16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i16>, i32 } @llvm.vp.load.ff.nxv2i16.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i16>, i32 } @vploadff_nxv4i16(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i16>, i32 } @llvm.vp.load.ff.nxv4i16.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i16>, i32 } @vploadff_nxv4i16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i16>, i32 } @llvm.vp.load.ff.nxv4i16.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i16>, i32 } @vploadff_nxv8i16(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i16>, i32 } @llvm.vp.load.ff.nxv8i16.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i16>, i32 } @vploadff_nxv8i16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i16>, i32 } @llvm.vp.load.ff.nxv8i16.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x i16>, i32 } @vploadff_nxv16i16(ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x i16>, i32 } @llvm.vp.load.ff.nxv16i16.p0(ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
|
|
ret { <vscale x 16 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x i16>, i32 } @vploadff_nxv16i16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16i16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x i16>, i32 } @llvm.vp.load.ff.nxv16i16.p0(ptr %ptr, <vscale x 16 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 16 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x i16>, i32 } @vploadff_nxv32i16(ptr %ptr, <vscale x 32 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x i16>, i32 } @llvm.vp.load.ff.nxv32i16.p0(ptr %ptr, <vscale x 32 x i1> %m, i32 %evl)
|
|
ret { <vscale x 32 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x i16>, i32 } @vploadff_nxv32i16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32i16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x i16>, i32 } @llvm.vp.load.ff.nxv32i16.p0(ptr %ptr, <vscale x 32 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 32 x i16>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x i32>, i32 } @vploadff_nxv1i32(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i32>, i32 } @llvm.vp.load.ff.nxv1i32.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x i32>, i32 } @vploadff_nxv1i32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i32>, i32 } @llvm.vp.load.ff.nxv1i32.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i32>, i32 } @vploadff_nxv2i32(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i32>, i32 } @llvm.vp.load.ff.nxv2i32.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i32>, i32 } @vploadff_nxv2i32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i32>, i32 } @llvm.vp.load.ff.nxv2i32.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i32>, i32 } @vploadff_nxv4i32(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i32>, i32 } @llvm.vp.load.ff.nxv4i32.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i32>, i32 } @vploadff_nxv4i32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i32>, i32 } @llvm.vp.load.ff.nxv4i32.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i32>, i32 } @vploadff_nxv8i32(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m4, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i32>, i32 } @llvm.vp.load.ff.nxv8i32.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i32>, i32 } @vploadff_nxv8i32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m4, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i32>, i32 } @llvm.vp.load.ff.nxv8i32.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x i32>, i32 } @vploadff_nxv16i32(ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x i32>, i32 } @llvm.vp.load.ff.nxv16i32.p0(ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
|
|
ret { <vscale x 16 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x i32>, i32 } @vploadff_nxv16i32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16i32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x i32>, i32 } @llvm.vp.load.ff.nxv16i32.p0(ptr %ptr, <vscale x 16 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 16 x i32>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x i64>, i32 } @vploadff_nxv1i64(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i64>, i32 } @llvm.vp.load.ff.nxv1i64.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x i64>, i32 } @vploadff_nxv1i64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1i64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x i64>, i32 } @llvm.vp.load.ff.nxv1i64.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i64>, i32 } @vploadff_nxv2i64(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m2, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i64>, i32 } @llvm.vp.load.ff.nxv2i64.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x i64>, i32 } @vploadff_nxv2i64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2i64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m2, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x i64>, i32 } @llvm.vp.load.ff.nxv2i64.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i64>, i32 } @vploadff_nxv4i64(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m4, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i64>, i32 } @llvm.vp.load.ff.nxv4i64.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x i64>, i32 } @vploadff_nxv4i64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4i64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m4, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x i64>, i32 } @llvm.vp.load.ff.nxv4i64.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i64>, i32 } @vploadff_nxv8i64(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m8, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i64>, i32 } @llvm.vp.load.ff.nxv8i64.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x i64>, i32 } @vploadff_nxv8i64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8i64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m8, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x i64>, i32 } @llvm.vp.load.ff.nxv8i64.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x i64>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x half>, i32 } @vploadff_nxv1f16(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x half>, i32 } @llvm.vp.load.ff.nxv1f16.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x half>, i32 } @vploadff_nxv1f16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1f16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x half>, i32 } @llvm.vp.load.ff.nxv1f16.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x half>, i32 } @vploadff_nxv2f16(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x half>, i32 } @llvm.vp.load.ff.nxv2f16.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x half>, i32 } @vploadff_nxv2f16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2f16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x half>, i32 } @llvm.vp.load.ff.nxv2f16.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x half>, i32 } @vploadff_nxv4f16(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x half>, i32 } @llvm.vp.load.ff.nxv4f16.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x half>, i32 } @vploadff_nxv4f16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4f16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x half>, i32 } @llvm.vp.load.ff.nxv4f16.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x half>, i32 } @vploadff_nxv8f16(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x half>, i32 } @llvm.vp.load.ff.nxv8f16.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x half>, i32 } @vploadff_nxv8f16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8f16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x half>, i32 } @llvm.vp.load.ff.nxv8f16.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x half>, i32 } @vploadff_nxv16f16(ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x half>, i32 } @llvm.vp.load.ff.nxv16f16.p0(ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
|
|
ret { <vscale x 16 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x half>, i32 } @vploadff_nxv16f16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16f16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x half>, i32 } @llvm.vp.load.ff.nxv16f16.p0(ptr %ptr, <vscale x 16 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 16 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x half>, i32 } @vploadff_nxv32f16(ptr %ptr, <vscale x 32 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x half>, i32 } @llvm.vp.load.ff.nxv32f16.p0(ptr %ptr, <vscale x 32 x i1> %m, i32 %evl)
|
|
ret { <vscale x 32 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x half>, i32 } @vploadff_nxv32f16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32f16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x half>, i32 } @llvm.vp.load.ff.nxv32f16.p0(ptr %ptr, <vscale x 32 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 32 x half>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x float>, i32 } @vploadff_nxv1f32(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x float>, i32 } @llvm.vp.load.ff.nxv1f32.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x float>, i32 } @vploadff_nxv1f32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1f32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x float>, i32 } @llvm.vp.load.ff.nxv1f32.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x float>, i32 } @vploadff_nxv2f32(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x float>, i32 } @llvm.vp.load.ff.nxv2f32.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x float>, i32 } @vploadff_nxv2f32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2f32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x float>, i32 } @llvm.vp.load.ff.nxv2f32.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x float>, i32 } @vploadff_nxv4f32(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x float>, i32 } @llvm.vp.load.ff.nxv4f32.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x float>, i32 } @vploadff_nxv4f32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4f32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m2, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x float>, i32 } @llvm.vp.load.ff.nxv4f32.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x float>, i32 } @vploadff_nxv8f32(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m4, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x float>, i32 } @llvm.vp.load.ff.nxv8f32.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x float>, i32 } @vploadff_nxv8f32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8f32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m4, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x float>, i32 } @llvm.vp.load.ff.nxv8f32.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x float>, i32 } @vploadff_nxv16f32(ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16f32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x float>, i32 } @llvm.vp.load.ff.nxv16f32.p0(ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
|
|
ret { <vscale x 16 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x float>, i32 } @vploadff_nxv16f32_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16f32_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, ma
|
|
; CHECK-NEXT: vle32ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x float>, i32 } @llvm.vp.load.ff.nxv16f32.p0(ptr %ptr, <vscale x 16 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 16 x float>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x double>, i32 } @vploadff_nxv1f64(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x double>, i32 } @llvm.vp.load.ff.nxv1f64.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x double>, i32 } @vploadff_nxv1f64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1f64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x double>, i32 } @llvm.vp.load.ff.nxv1f64.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x double>, i32 } @vploadff_nxv2f64(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m2, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x double>, i32 } @llvm.vp.load.ff.nxv2f64.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x double>, i32 } @vploadff_nxv2f64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2f64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m2, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x double>, i32 } @llvm.vp.load.ff.nxv2f64.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x double>, i32 } @vploadff_nxv4f64(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m4, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x double>, i32 } @llvm.vp.load.ff.nxv4f64.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x double>, i32 } @vploadff_nxv4f64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4f64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m4, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x double>, i32 } @llvm.vp.load.ff.nxv4f64.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x double>, i32 } @vploadff_nxv8f64(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8f64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m8, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x double>, i32 } @llvm.vp.load.ff.nxv8f64.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x double>, i32 } @vploadff_nxv8f64_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8f64_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e64, m8, ta, ma
|
|
; CHECK-NEXT: vle64ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x double>, i32 } @llvm.vp.load.ff.nxv8f64.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x double>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x bfloat>, i32 } @vploadff_nxv1bf16(ptr %ptr, <vscale x 1 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x bfloat>, i32 } @llvm.vp.load.ff.nxv1bf16.p0(ptr %ptr, <vscale x 1 x i1> %m, i32 %evl)
|
|
ret { <vscale x 1 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 1 x bfloat>, i32 } @vploadff_nxv1bf16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv1bf16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 1 x bfloat>, i32 } @llvm.vp.load.ff.nxv1bf16.p0(ptr %ptr, <vscale x 1 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 1 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x bfloat>, i32 } @vploadff_nxv2bf16(ptr %ptr, <vscale x 2 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x bfloat>, i32 } @llvm.vp.load.ff.nxv2bf16.p0(ptr %ptr, <vscale x 2 x i1> %m, i32 %evl)
|
|
ret { <vscale x 2 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 2 x bfloat>, i32 } @vploadff_nxv2bf16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv2bf16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 2 x bfloat>, i32 } @llvm.vp.load.ff.nxv2bf16.p0(ptr %ptr, <vscale x 2 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 2 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x bfloat>, i32 } @vploadff_nxv4bf16(ptr %ptr, <vscale x 4 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x bfloat>, i32 } @llvm.vp.load.ff.nxv4bf16.p0(ptr %ptr, <vscale x 4 x i1> %m, i32 %evl)
|
|
ret { <vscale x 4 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 4 x bfloat>, i32 } @vploadff_nxv4bf16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv4bf16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 4 x bfloat>, i32 } @llvm.vp.load.ff.nxv4bf16.p0(ptr %ptr, <vscale x 4 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 4 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x bfloat>, i32 } @vploadff_nxv8bf16(ptr %ptr, <vscale x 8 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x bfloat>, i32 } @llvm.vp.load.ff.nxv8bf16.p0(ptr %ptr, <vscale x 8 x i1> %m, i32 %evl)
|
|
ret { <vscale x 8 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 8 x bfloat>, i32 } @vploadff_nxv8bf16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv8bf16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 8 x bfloat>, i32 } @llvm.vp.load.ff.nxv8bf16.p0(ptr %ptr, <vscale x 8 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 8 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x bfloat>, i32 } @vploadff_nxv16bf16(ptr %ptr, <vscale x 16 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x bfloat>, i32 } @llvm.vp.load.ff.nxv16bf16.p0(ptr %ptr, <vscale x 16 x i1> %m, i32 %evl)
|
|
ret { <vscale x 16 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 16 x bfloat>, i32 } @vploadff_nxv16bf16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv16bf16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 16 x bfloat>, i32 } @llvm.vp.load.ff.nxv16bf16.p0(ptr %ptr, <vscale x 16 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 16 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x bfloat>, i32 } @vploadff_nxv32bf16(ptr %ptr, <vscale x 32 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x bfloat>, i32 } @llvm.vp.load.ff.nxv32bf16.p0(ptr %ptr, <vscale x 32 x i1> %m, i32 %evl)
|
|
ret { <vscale x 32 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 32 x bfloat>, i32 } @vploadff_nxv32bf16_allones_mask(ptr %ptr, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv32bf16_allones_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, ma
|
|
; CHECK-NEXT: vle16ff.v v8, (a0)
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 32 x bfloat>, i32 } @llvm.vp.load.ff.nxv32bf16.p0(ptr %ptr, <vscale x 32 x i1> splat (i1 true), i32 %evl)
|
|
ret { <vscale x 32 x bfloat>, i32 } %load
|
|
}
|
|
|
|
define { <vscale x 3 x i8>, i32 } @vploadff_nxv3i8(ptr %ptr, <vscale x 3 x i1> %m, i32 zeroext %evl) {
|
|
; CHECK-LABEL: vploadff_nxv3i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
|
|
; CHECK-NEXT: vle8ff.v v8, (a0), v0.t
|
|
; CHECK-NEXT: csrr a0, vl
|
|
; CHECK-NEXT: ret
|
|
%load = call { <vscale x 3 x i8>, i32 } @llvm.vp.load.ff.nxv3i8.p0(ptr %ptr, <vscale x 3 x i1> %m, i32 %evl)
|
|
ret { <vscale x 3 x i8>, i32 } %load
|
|
}
|