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/AArch64/sve-intrinsics-ff-gather-loads-vector-base-imm-offset.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

398 lines
21 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -verify-machineinstrs < %s | FileCheck %s
;
; LDFF1B, LDFF1W, LDFF1H, LDFF1D: vector base + immediate offset (index)
; e.g. ldff1h { z0.s }, p0/z, [z0.s, #16]
;
; LDFF1B
define <vscale x 4 x i32> @gldff1b_s_imm_offset(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1b_s_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1b { z0.s }, p0/z, [z0.s, #16]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i8.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 16)
%res = zext <vscale x 4 x i8> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1b_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1b_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1b { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i8.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
%res = zext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1H
define <vscale x 4 x i32> @gldff1h_s_imm_offset(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1h_s_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1h { z0.s }, p0/z, [z0.s, #16]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i16.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 16)
%res = zext <vscale x 4 x i16> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1h_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1h_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1h { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i16.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
%res = zext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1W
define <vscale x 4 x i32> @gldff1w_s_imm_offset(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1w_s_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1w { z0.s }, p0/z, [z0.s, #16]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i32.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 16)
ret <vscale x 4 x i32> %load
}
define <vscale x 2 x i64> @gldff1w_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1w_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1w { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i32.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
%res = zext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 4 x float> @gldff1w_s_imm_offset_float(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1w_s_imm_offset_float:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1w { z0.s }, p0/z, [z0.s, #16]
; CHECK-NEXT: ret
%load = call <vscale x 4 x float> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4f32.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 16)
ret <vscale x 4 x float> %load
}
; LDFF1D
define <vscale x 2 x i64> @gldff1d_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1d_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1d { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i64> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i64.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
ret <vscale x 2 x i64> %load
}
define <vscale x 2 x double> @gldff1d_d_imm_offset_double(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1d_d_imm_offset_double:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1d { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x double> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2f64.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
ret <vscale x 2 x double> %load
}
;
; LDFF1SB, LDFF1SW, LDFF1SH: vector base + immediate offset (index)
; e.g. ldff1sh { z0.s }, p0/z, [z0.s, #16]
;
; LDFF1SB
define <vscale x 4 x i32> @gldff1sb_s_imm_offset(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1sb_s_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sb { z0.s }, p0/z, [z0.s, #16]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i8.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 16)
%res = sext <vscale x 4 x i8> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1sb_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1sb_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sb { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i8.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
%res = sext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1SH
define <vscale x 4 x i32> @gldff1sh_s_imm_offset(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1sh_s_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sh { z0.s }, p0/z, [z0.s, #16]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i16.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 16)
%res = sext <vscale x 4 x i16> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1sh_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1sh_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sh { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i16.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
%res = sext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1SW
define <vscale x 2 x i64> @gldff1sw_d_imm_offset(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1sw_d_imm_offset:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sw { z0.d }, p0/z, [z0.d, #16]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i32.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 16)
%res = sext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
;
; LDFF1B, LDFF1W, LDFF1H, LDFF1D: vector base + out of range immediate offset
; e.g. ldff1b { z0.d }, p0/z, [x0, z0.d]
;
; LDFF1B
define <vscale x 4 x i32> @gldff1b_s_imm_offset_out_of_range(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1b_s_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32
; CHECK-NEXT: ldff1b { z0.s }, p0/z, [x8, z0.s, uxtw]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i8.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 32)
%res = zext <vscale x 4 x i8> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1b_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1b_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32
; CHECK-NEXT: ldff1b { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i8.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 32)
%res = zext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1H
define <vscale x 4 x i32> @gldff1h_s_imm_offset_out_of_range(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1h_s_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #63
; CHECK-NEXT: ldff1h { z0.s }, p0/z, [x8, z0.s, uxtw]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i16.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 63)
%res = zext <vscale x 4 x i16> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1h_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1h_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #63
; CHECK-NEXT: ldff1h { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i16.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 63)
%res = zext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1W
define <vscale x 4 x i32> @gldff1w_s_imm_offset_out_of_range(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1w_s_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #125
; CHECK-NEXT: ldff1w { z0.s }, p0/z, [x8, z0.s, uxtw]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i32.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 125)
ret <vscale x 4 x i32> %load
}
define <vscale x 2 x i64> @gldff1w_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1w_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #125
; CHECK-NEXT: ldff1w { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i32.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 125)
%res = zext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 4 x float> @gldff1w_s_imm_offset_out_of_range_float(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1w_s_imm_offset_out_of_range_float:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #125
; CHECK-NEXT: ldff1w { z0.s }, p0/z, [x8, z0.s, uxtw]
; CHECK-NEXT: ret
%load = call <vscale x 4 x float> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4f32.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 125)
ret <vscale x 4 x float> %load
}
; LDFF1D
define <vscale x 2 x i64> @gldff1d_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1d_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #249
; CHECK-NEXT: ldff1d { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i64> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i64.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 249)
ret <vscale x 2 x i64> %load
}
define <vscale x 2 x double> @gldff1d_d_imm_offset_out_of_range_double(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1d_d_imm_offset_out_of_range_double:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #249
; CHECK-NEXT: ldff1d { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x double> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2f64.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 249)
ret <vscale x 2 x double> %load
}
;
; LDFF1SB, LDFF1SW, LDFF1SH: vector base + out of range immediate offset
; e.g. ldff1sb { z0.s }, p0/z, [x8, z0.s, uxtw]
;
; LDFF1SB
define <vscale x 4 x i32> @gldff1sb_s_imm_offset_out_of_range(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1sb_s_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32
; CHECK-NEXT: ldff1sb { z0.s }, p0/z, [x8, z0.s, uxtw]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i8.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 32)
%res = sext <vscale x 4 x i8> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1sb_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1sb_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #32
; CHECK-NEXT: ldff1sb { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i8.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 32)
%res = sext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1SH
define <vscale x 4 x i32> @gldff1sh_s_imm_offset_out_of_range(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %base) {
; CHECK-LABEL: gldff1sh_s_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #63
; CHECK-NEXT: ldff1sh { z0.s }, p0/z, [x8, z0.s, uxtw]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i16.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %base,
i64 63)
%res = sext <vscale x 4 x i16> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @gldff1sh_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1sh_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #63
; CHECK-NEXT: ldff1sh { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i16.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 63)
%res = sext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1SW
define <vscale x 2 x i64> @gldff1sw_d_imm_offset_out_of_range(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %base) {
; CHECK-LABEL: gldff1sw_d_imm_offset_out_of_range:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #125
; CHECK-NEXT: ldff1sw { z0.d }, p0/z, [x8, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i32.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %base,
i64 125)
%res = sext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
; LDFF1B/LDFF1SB
declare <vscale x 4 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i8.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i64)
declare <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i8.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i64)
; LDFF1H/LDFF1SH
declare <vscale x 4 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i16.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i64)
declare <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i16.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i64)
; LDFF1W/LDFF1SW
declare <vscale x 4 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4i32.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i64)
declare <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i32.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i64)
declare <vscale x 4 x float> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv4f32.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i64)
; LDFF1D
declare <vscale x 2 x i64> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2i64.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i64)
declare <vscale x 2 x double> @llvm.aarch64.sve.ldff1.gather.scalar.offset.nxv2f64.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i64)
Reference in new issue View Git Blame Copy Permalink