1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+m,+v,+zfh,+experimental-zvfh,+f,+d -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+m,+v,+zfh,+experimental-zvfh,+f,+d -verify-machineinstrs < %s | FileCheck %s
; Check that we are able to legalize scalable-vector loads that require widening.
define <vscale x 3 x i8> @load_nxv3i8(<vscale x 3 x i8>* %ptr) {
; CHECK-LABEL: load_nxv3i8:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 3
; CHECK-NEXT: slli a2, a1, 1
; CHECK-NEXT: add a1, a2, a1
; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
; CHECK-NEXT: vle8.v v8, (a0)
; CHECK-NEXT: ret
%v = load <vscale x 3 x i8>, <vscale x 3 x i8>* %ptr
ret <vscale x 3 x i8> %v
}
define <vscale x 5 x half> @load_nxv5f16(<vscale x 5 x half>* %ptr) {
; CHECK-LABEL: load_nxv5f16:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 3
; CHECK-NEXT: slli a2, a1, 2
; CHECK-NEXT: add a1, a2, a1
; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: ret
%v = load <vscale x 5 x half>, <vscale x 5 x half>* %ptr
ret <vscale x 5 x half> %v
}
define <vscale x 7 x half> @load_nxv7f16(<vscale x 7 x half>* %ptr, <vscale x 7 x half>* %out) {
; CHECK-LABEL: load_nxv7f16:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: srli a3, a2, 3
; CHECK-NEXT: sub a2, a2, a3
; CHECK-NEXT: vsetvli zero, a2, e16, m2, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: vse16.v v8, (a1)
; CHECK-NEXT: ret
%v = load <vscale x 7 x half>, <vscale x 7 x half>* %ptr
store <vscale x 7 x half> %v, <vscale x 7 x half>* %out
ret <vscale x 7 x half> %v
}
|
