2017-02-15 07:23:12 +08:00
|
|
|
# mach: aarch64
|
|
|
|
|
|
|
|
|
|
# Check the vector multiply add instruction: mla.
|
|
|
|
|
|
|
|
|
|
.include "testutils.inc"
|
|
|
|
|
|
Fix ldn/stn multiple instructions. Fix testcases with unaligned data.
sim/aarch64/
* simulator.c (vec_load): Add M argument. Rewrite to iterate over
registers based on structure size.
(LD4, LD3, LD2, LD1_2, LD1_3, LD1_4): Pass new arg to vec_load.
(LD1_1): Replace with call to vec_load.
(vec_store): Add new M argument. Rewrite to iterate over registers
based on structure size.
(ST4, ST3, ST2, ST1_2, ST1_3, ST1_4): Pass new arg to vec_store.
(ST1_1): Replace with call to vec_store.
sim/testsuite/sim/aarch64/
* fcvtz.s, fstur.s, ldn_single.s, ldnr.s, mla.s, mls.s, uzp.s: Align
data.
* sumulh.s: Delete unnecessary data alignment.
* stn_single.s: Align data. Fix unaligned ldr insns. Adjust cmp
arguments to match change.
* ldn_multiple.s, stn_multiple.s: New.
2017-04-23 07:36:01 +08:00
|
|
|
.data
|
|
|
|
|
.align 4
|
2017-02-15 07:23:12 +08:00
|
|
|
input:
|
|
|
|
|
.word 0x04030201
|
|
|
|
|
.word 0x08070605
|
|
|
|
|
.word 0x0c0b0a09
|
|
|
|
|
.word 0x100f0e0d
|
|
|
|
|
m8b:
|
|
|
|
|
.word 0x110a0502
|
|
|
|
|
.word 0x4132251a
|
|
|
|
|
m16b:
|
|
|
|
|
.word 0x110a0502
|
|
|
|
|
.word 0x4132251a
|
|
|
|
|
.word 0x917a6552
|
|
|
|
|
.word 0x01e2c5aa
|
|
|
|
|
m4h:
|
|
|
|
|
.word 0x180a0402
|
|
|
|
|
.word 0x70323c1a
|
|
|
|
|
m8h:
|
|
|
|
|
.word 0x180a0402
|
|
|
|
|
.word 0x70323c1a
|
|
|
|
|
.word 0x087ab452
|
|
|
|
|
.word 0xe0e26caa
|
|
|
|
|
m2s:
|
|
|
|
|
.word 0x140a0402
|
|
|
|
|
.word 0xa46a3c1a
|
|
|
|
|
m4s:
|
|
|
|
|
.word 0x140a0402
|
|
|
|
|
.word 0xa46a3c1a
|
|
|
|
|
.word 0xb52ab452
|
|
|
|
|
.word 0x464b6caa
|
|
|
|
|
|
|
|
|
|
start
|
|
|
|
|
adrp x0, input
|
|
|
|
|
ldr q0, [x0, #:lo12:input]
|
|
|
|
|
|
|
|
|
|
movi v1.8b, #1
|
|
|
|
|
mla v1.8b, v0.8b, v0.8b
|
|
|
|
|
mov x1, v1.d[0]
|
|
|
|
|
adrp x3, m8b
|
|
|
|
|
ldr x4, [x3, #:lo12:m8b]
|
|
|
|
|
cmp x1, x4
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
|
|
|
|
|
movi v1.16b, #1
|
|
|
|
|
mla v1.16b, v0.16b, v0.16b
|
|
|
|
|
mov x1, v1.d[0]
|
|
|
|
|
mov x2, v1.d[1]
|
|
|
|
|
adrp x3, m16b
|
|
|
|
|
ldr x4, [x3, #:lo12:m16b]
|
|
|
|
|
cmp x1, x4
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
ldr x5, [x3, #:lo12:m16b+8]
|
|
|
|
|
cmp x2, x5
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
|
|
|
|
|
movi v1.4h, #1
|
|
|
|
|
mla v1.4h, v0.4h, v0.4h
|
|
|
|
|
mov x1, v1.d[0]
|
|
|
|
|
adrp x3, m4h
|
|
|
|
|
ldr x4, [x3, #:lo12:m4h]
|
|
|
|
|
cmp x1, x4
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
|
|
|
|
|
movi v1.8h, #1
|
|
|
|
|
mla v1.8h, v0.8h, v0.8h
|
|
|
|
|
mov x1, v1.d[0]
|
|
|
|
|
mov x2, v1.d[1]
|
|
|
|
|
adrp x3, m8h
|
|
|
|
|
ldr x4, [x3, #:lo12:m8h]
|
|
|
|
|
cmp x1, x4
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
ldr x5, [x3, #:lo12:m8h+8]
|
|
|
|
|
cmp x2, x5
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
|
|
|
|
|
movi v1.2s, #1
|
|
|
|
|
mla v1.2s, v0.2s, v0.2s
|
|
|
|
|
mov x1, v1.d[0]
|
|
|
|
|
adrp x3, m2s
|
|
|
|
|
ldr x4, [x3, #:lo12:m2s]
|
|
|
|
|
cmp x1, x4
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
|
|
|
|
|
movi v1.4s, #1
|
|
|
|
|
mla v1.4s, v0.4s, v0.4s
|
|
|
|
|
mov x1, v1.d[0]
|
|
|
|
|
mov x2, v1.d[1]
|
|
|
|
|
adrp x3, m4s
|
|
|
|
|
ldr x4, [x3, #:lo12:m4s]
|
|
|
|
|
cmp x1, x4
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
ldr x5, [x3, #:lo12:m4s+8]
|
|
|
|
|
cmp x2, x5
|
|
|
|
|
bne .Lfailure
|
|
|
|
|
|
|
|
|
|
pass
|
|
|
|
|
.Lfailure:
|
|
|
|
|
fail
|
