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/fixed-vectors-expandload-int.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

267 lines
10 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc -verify-machineinstrs -mtriple=riscv32 -mattr=+m,+v %s -o - \
; RUN: | FileCheck %s --check-prefixes=CHECK,CHECK-RV32
; RUN: llc -verify-machineinstrs -mtriple=riscv64 -mattr=+m,+v %s -o - \
; RUN: | FileCheck %s --check-prefixes=CHECK,CHECK-RV64
define <1 x i8> @expandload_v1i8(ptr %base, <1 x i8> %src0, <1 x i1> %mask) {
; CHECK-LABEL: expandload_v1i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e8, mf8, ta, ma
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <1 x i8> @llvm.masked.expandload.v1i8(ptr %base, <1 x i1> %mask, <1 x i8> %src0)
ret <1 x i8>%res
}
define <2 x i8> @expandload_v2i8(ptr %base, <2 x i8> %src0, <2 x i1> %mask) {
; CHECK-LABEL: expandload_v2i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e8, mf8, ta, ma
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <2 x i8> @llvm.masked.expandload.v2i8(ptr %base, <2 x i1> %mask, <2 x i8> %src0)
ret <2 x i8>%res
}
define <4 x i8> @expandload_v4i8(ptr %base, <4 x i8> %src0, <4 x i1> %mask) {
; CHECK-LABEL: expandload_v4i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e8, mf4, ta, ma
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <4 x i8> @llvm.masked.expandload.v4i8(ptr %base, <4 x i1> %mask, <4 x i8> %src0)
ret <4 x i8>%res
}
define <8 x i8> @expandload_v8i8(ptr %base, <8 x i8> %src0, <8 x i1> %mask) {
; CHECK-LABEL: expandload_v8i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <8 x i8> @llvm.masked.expandload.v8i8(ptr %base, <8 x i1> %mask, <8 x i8> %src0)
ret <8 x i8>%res
}
define <7 x i8> @expandload_v7i8(ptr %base, <7 x i1> %mask) {
; CHECK-LABEL: expandload_v7i8:
; CHECK: # %bb.0:
; CHECK-NEXT: li a1, 127
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vmv.s.x v8, a1
; CHECK-NEXT: vmand.mm v0, v0, v8
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <7 x i8> @llvm.masked.expandload.v7i8(ptr %base, <7 x i1> %mask, <7 x i8> poison)
ret <7 x i8>%res
}
define <1 x i16> @expandload_v1i16(ptr %base, <1 x i16> %src0, <1 x i1> %mask) {
; CHECK-LABEL: expandload_v1i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
; CHECK-NEXT: vle16.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <1 x i16> @llvm.masked.expandload.v1i16(ptr align 2 %base, <1 x i1> %mask, <1 x i16> %src0)
ret <1 x i16>%res
}
define <2 x i16> @expandload_v2i16(ptr %base, <2 x i16> %src0, <2 x i1> %mask) {
; CHECK-LABEL: expandload_v2i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
; CHECK-NEXT: vle16.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <2 x i16> @llvm.masked.expandload.v2i16(ptr align 2 %base, <2 x i1> %mask, <2 x i16> %src0)
ret <2 x i16>%res
}
define <4 x i16> @expandload_v4i16(ptr %base, <4 x i16> %src0, <4 x i1> %mask) {
; CHECK-LABEL: expandload_v4i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
; CHECK-NEXT: vle16.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <4 x i16> @llvm.masked.expandload.v4i16(ptr align 2 %base, <4 x i1> %mask, <4 x i16> %src0)
ret <4 x i16>%res
}
define <8 x i16> @expandload_v8i16(ptr %base, <8 x i16> %src0, <8 x i1> %mask) {
; CHECK-LABEL: expandload_v8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
; CHECK-NEXT: vle16.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <8 x i16> @llvm.masked.expandload.v8i16(ptr align 2 %base, <8 x i1> %mask, <8 x i16> %src0)
ret <8 x i16>%res
}
define <1 x i32> @expandload_v1i32(ptr %base, <1 x i32> %src0, <1 x i1> %mask) {
; CHECK-LABEL: expandload_v1i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, ta, ma
; CHECK-NEXT: vle32.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <1 x i32> @llvm.masked.expandload.v1i32(ptr align 4 %base, <1 x i1> %mask, <1 x i32> %src0)
ret <1 x i32>%res
}
define <2 x i32> @expandload_v2i32(ptr %base, <2 x i32> %src0, <2 x i1> %mask) {
; CHECK-LABEL: expandload_v2i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e32, mf2, ta, ma
; CHECK-NEXT: vle32.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <2 x i32> @llvm.masked.expandload.v2i32(ptr align 4 %base, <2 x i1> %mask, <2 x i32> %src0)
ret <2 x i32>%res
}
define <4 x i32> @expandload_v4i32(ptr %base, <4 x i32> %src0, <4 x i1> %mask) {
; CHECK-LABEL: expandload_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
; CHECK-NEXT: vle32.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <4 x i32> @llvm.masked.expandload.v4i32(ptr align 4 %base, <4 x i1> %mask, <4 x i32> %src0)
ret <4 x i32>%res
}
define <8 x i32> @expandload_v8i32(ptr %base, <8 x i32> %src0, <8 x i1> %mask) {
; CHECK-LABEL: expandload_v8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e32, m2, ta, ma
; CHECK-NEXT: vle32.v v10, (a0)
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; CHECK-NEXT: viota.m v12, v0
; CHECK-NEXT: vrgather.vv v8, v10, v12, v0.t
; CHECK-NEXT: ret
%res = call <8 x i32> @llvm.masked.expandload.v8i32(ptr align 4 %base, <8 x i1> %mask, <8 x i32> %src0)
ret <8 x i32>%res
}
define <1 x i64> @expandload_v1i64(ptr %base, <1 x i64> %src0, <1 x i1> %mask) {
; CHECK-LABEL: expandload_v1i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
; CHECK-NEXT: vle64.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <1 x i64> @llvm.masked.expandload.v1i64(ptr align 8 %base, <1 x i1> %mask, <1 x i64> %src0)
ret <1 x i64>%res
}
define <2 x i64> @expandload_v2i64(ptr %base, <2 x i64> %src0, <2 x i1> %mask) {
; CHECK-LABEL: expandload_v2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
; CHECK-NEXT: vle64.v v9, (a0)
; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; CHECK-NEXT: viota.m v10, v0
; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
; CHECK-NEXT: ret
%res = call <2 x i64> @llvm.masked.expandload.v2i64(ptr align 8 %base, <2 x i1> %mask, <2 x i64> %src0)
ret <2 x i64>%res
}
define <4 x i64> @expandload_v4i64(ptr %base, <4 x i64> %src0, <4 x i1> %mask) {
; CHECK-LABEL: expandload_v4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e64, m2, ta, ma
; CHECK-NEXT: vle64.v v10, (a0)
; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, mu
; CHECK-NEXT: viota.m v12, v0
; CHECK-NEXT: vrgather.vv v8, v10, v12, v0.t
; CHECK-NEXT: ret
%res = call <4 x i64> @llvm.masked.expandload.v4i64(ptr align 8 %base, <4 x i1> %mask, <4 x i64> %src0)
ret <4 x i64>%res
}
define <8 x i64> @expandload_v8i64(ptr %base, <8 x i64> %src0, <8 x i1> %mask) {
; CHECK-LABEL: expandload_v8i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vcpop.m a1, v0
; CHECK-NEXT: vsetvli zero, a1, e64, m4, ta, ma
; CHECK-NEXT: vle64.v v12, (a0)
; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; CHECK-NEXT: viota.m v16, v0
; CHECK-NEXT: vrgather.vv v8, v12, v16, v0.t
; CHECK-NEXT: ret
%res = call <8 x i64> @llvm.masked.expandload.v8i64(ptr align 8 %base, <8 x i1> %mask, <8 x i64> %src0)
ret <8 x i64>%res
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; CHECK-RV32: {{.*}}
; CHECK-RV64: {{.*}}
Reference in new issue View Git Blame Copy Permalink