https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88492
ptomsich at gcc dot gnu.org changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |ptomsich at gcc dot gnu.org
--- Comment #6 from ptomsich at gcc dot gnu.org ---
With the current master, the test case generates (with -mcpu=neoverse-n1):
.arch armv8.2-a+crc+fp16+rcpc+dotprod+profile
.file "pr88492.c"
.text
.align 2
.p2align 5,,15
.global test_slp
.type test_slp, %function
test_slp:
.LFB0:
.cfi_startproc
ldr q2, [x0]
adrp x1, .LC0
ldr q16, [x1, #:lo12:.LC0]
uxtl v4.8h, v2.8b
uxtl2 v2.8h, v2.16b
uxtl v0.4s, v4.4h
uxtl v6.4s, v2.4h
uxtl2 v4.4s, v4.8h
uxtl2 v2.4s, v2.8h
mov v1.16b, v0.16b
mov v7.16b, v6.16b
mov v5.16b, v4.16b
mov v3.16b, v2.16b
tbl v0.16b, {v0.16b - v1.16b}, v16.16b
tbl v6.16b, {v6.16b - v7.16b}, v16.16b
tbl v4.16b, {v4.16b - v5.16b}, v16.16b
tbl v2.16b, {v2.16b - v3.16b}, v16.16b
add v0.4s, v0.4s, v4.4s
add v6.4s, v6.4s, v2.4s
add v0.4s, v0.4s, v6.4s
addv s0, v0.4s
fmov w0, s0
ret
.cfi_endproc
.LFE0:
.size test_slp, .-test_slp
which contrasts with LLVM13 (with -mcpu=neoverse-n1):
test_slp: // @test_slp
.cfi_startproc
// %bb.0: // %entry
ldr q0, [x0]
movi v1.16b, #1
movi v2.2d, #0000000000000000
udot v2.4s, v0.16b, v1.16b
addv s0, v2.4s
fmov w0, s0
ret
.Lfunc_end0:
.size test_slp, .Lfunc_end0-test_slp
or (LLVM13 w/o the mcpu-option):
.type test_slp,@function
test_slp: // @test_slp
.cfi_startproc
// %bb.0: // %entry
ldr q0, [x0]
ushll2 v1.8h, v0.16b, #0
ushll v0.8h, v0.8b, #0
uaddl2 v2.4s, v0.8h, v1.8h
uaddl v0.4s, v0.4h, v1.4h
add v0.4s, v0.4s, v2.4s
addv s0, v0.4s
fmov w0, s0
ret
.Lfunc_end0:
.size test_slp, .Lfunc_end0-test_slp
