llvm-project/llvm/test/CodeGen/AArch64/sve2-intrinsics-nt-scatter-...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

71 lines
3.4 KiB
LLVM
Raw Normal View History

[AArch64][SVE] Add intrinsics for non-temporal gather-loads/scatter-stores Summary: This patch adds the following LLVM IR intrinsics for SVE: 1. non-temporal gather loads * @llvm.aarch64.sve.ldnt1.gather * @llvm.aarch64.sve.ldnt1.gather.uxtw * @llvm.aarch64.sve.ldnt1.gather.scalar.offset 2. non-temporal scatter stores * @llvm.aarch64.sve.stnt1.scatter * @llvm.aarch64.sve.ldnt1.gather.uxtw * @llvm.aarch64.sve.ldnt1.gather.scalar.offset These intrinsic are mapped to the corresponding SVE instructions (example for half-words, zero-extending): * ldnt1h { z0.s }, p0/z, [z0.s, x0] * stnt1h { z0.s }, p0/z, [z0.s, x0] Note that for non-temporal gathers/scatters, the SVE spec defines only one instruction type: "vector + scalar". For this reason, we swap the arguments when processing intrinsics that implement the "scalar + vector" addressing mode: * @llvm.aarch64.sve.ldnt1.gather * @llvm.aarch64.sve.ldnt1.gather.uxtw * @llvm.aarch64.sve.stnt1.scatter * @llvm.aarch64.sve.ldnt1.gather.uxtw In other words, all intrinsics for gather-loads and scatter-stores implemented in this patch are mapped to the same load and store instruction, respectively. The sve2_mem_gldnt_vs multiclass (and it's counterpart for scatter stores) from SVEInstrFormats.td was split into: * sve2_mem_gldnt_vec_vs_32_ptrs (32bit wide base addresses) * sve2_mem_gldnt_vec_vs_62_ptrs (64bit wide base addresses) This is consistent with what we did for @llvm.aarch64.sve.ld1.scalar.offset and highlights the actual split in the spec and the implementation. Reviewed by: sdesmalen Differential Revision: https://reviews.llvm.org/D74858
2020-02-19 20:25:30 +08:00
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
;
; STNT1B, STNT1W, STNT1H, STNT1D: base + 64-bit unscaled offset
; e.g. stnt1h { z0.d }, p0, [z1.d, x0]
;
define void @sstnt1b_d(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, i8* %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sstnt1b_d:
; CHECK: stnt1b { z0.d }, p0, [z1.d, x0]
; CHECK-NEXT: ret
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i8>
call void @llvm.aarch64.sve.stnt1.scatter.nxv2i8(<vscale x 2 x i8> %data_trunc,
<vscale x 2 x i1> %pg,
i8* %base,
<vscale x 2 x i64> %b)
ret void
}
define void @sstnt1h_d(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, i16* %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sstnt1h_d:
; CHECK: stnt1h { z0.d }, p0, [z1.d, x0]
; CHECK-NEXT: ret
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i16>
call void @llvm.aarch64.sve.stnt1.scatter.nxv2i16(<vscale x 2 x i16> %data_trunc,
<vscale x 2 x i1> %pg,
i16* %base,
<vscale x 2 x i64> %b)
ret void
}
define void @sstnt1w_d(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, i32* %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sstnt1w_d:
; CHECK: stnt1w { z0.d }, p0, [z1.d, x0]
; CHECK-NEXT: ret
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i32>
call void @llvm.aarch64.sve.stnt1.scatter.nxv2i32(<vscale x 2 x i32> %data_trunc,
<vscale x 2 x i1> %pg,
i32* %base,
<vscale x 2 x i64> %b)
ret void
}
define void @sstnt1d_d(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, i64* %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sstnt1d_d:
; CHECK: stnt1d { z0.d }, p0, [z1.d, x0]
; CHECK-NEXT: ret
call void @llvm.aarch64.sve.stnt1.scatter.nxv2i64(<vscale x 2 x i64> %data,
<vscale x 2 x i1> %pg,
i64* %base,
<vscale x 2 x i64> %b)
ret void
}
define void @sstnt1d_d_double(<vscale x 2 x double> %data, <vscale x 2 x i1> %pg, double* %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: sstnt1d_d_double:
; CHECK: stnt1d { z0.d }, p0, [z1.d, x0]
; CHECK-NEXT: ret
call void @llvm.aarch64.sve.stnt1.scatter.nxv2f64(<vscale x 2 x double> %data,
<vscale x 2 x i1> %pg,
double* %base,
<vscale x 2 x i64> %b)
ret void
}
declare void @llvm.aarch64.sve.stnt1.scatter.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i1>, i8*, <vscale x 2 x i64>)
declare void @llvm.aarch64.sve.stnt1.scatter.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, i16*, <vscale x 2 x i64>)
declare void @llvm.aarch64.sve.stnt1.scatter.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, i32*, <vscale x 2 x i64>)
declare void @llvm.aarch64.sve.stnt1.scatter.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i64*, <vscale x 2 x i64>)
declare void @llvm.aarch64.sve.stnt1.scatter.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, double*, <vscale x 2 x i64>)