mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
859b066624
Lowers the llvm.masked.scatter intrinsics (scalar plus vector addressing mode only)
Changes included in this patch:
- Custom lowering for MSCATTER, which chooses the appropriate scatter store opcode to use.
Floating-point scatters are cast to integer, with patterns added to match FP reinterpret_casts.
- Added the getCanonicalIndexType function to convert redundant addressing
modes (e.g. scaling is redundant when accessing bytes)
- Tests with 32 & 64-bit scaled & unscaled offsets
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D90941
74 lines
3.8 KiB
LLVM
74 lines
3.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
|
|
|
|
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
; scaled 64-bit offsets
|
|
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
|
|
define void @masked_scatter_nxv2i16(<vscale x 2 x i16> %data, i16* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_nxv2i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [x0, z1.d, lsl #1]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i16, i16* %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2i16(<vscale x 2 x i16> %data, <vscale x 2 x i16*> %ptrs, i32 2, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2i32(<vscale x 2 x i32> %data, i32* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_nxv2i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [x0, z1.d, lsl #2]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i32, i32* %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2i32(<vscale x 2 x i32> %data, <vscale x 2 x i32*> %ptrs, i32 4, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2i64(<vscale x 2 x i64> %data, i64* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_nxv2i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d, lsl #3]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i64, i64* %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x i64*> %ptrs, i32 8, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2f16(<vscale x 2 x half> %data, half* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_nxv2f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [x0, z1.d, lsl #1]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr half, half* %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x half*> %ptrs, i32 2, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2f32(<vscale x 2 x float> %data, float* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_nxv2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [x0, z1.d, lsl #2]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr float, float* %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float> %data, <vscale x 2 x float*> %ptrs, i32 4, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2f64(<vscale x 2 x double> %data, double* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_nxv2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d, lsl #3]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr double, double* %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x double*> %ptrs, i32 8, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.masked.scatter.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16*>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32*>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64*>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half*>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float*>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double*>, i32, <vscale x 2 x i1>)
|