diff options
| author | Ard Biesheuvel <ard.biesheuvel@linaro.org> | 2019-02-26 12:36:18 +0100 |
|---|---|---|
| committer | Catalin Marinas <catalin.marinas@arm.com> | 2019-02-28 17:48:23 +0000 |
| commit | 335ebe3035b6fcb83c3f225bc5135300fc24c827 (patch) | |
| tree | 2f6f093da8a34e9969b6cab3dff85ef090b1363c /lib | |
| parent | 1ad3935b39da78a403e7df7a3813f866c731bc64 (diff) | |
| download | linux-335ebe3035b6fcb83c3f225bc5135300fc24c827.tar.gz linux-335ebe3035b6fcb83c3f225bc5135300fc24c827.tar.bz2 linux-335ebe3035b6fcb83c3f225bc5135300fc24c827.zip | |
lib/raid6: arm: optimize away a mask operation in NEON recovery routine
The NEON recovery code was modeled after the x86 SIMD code, and for
some reason, that code uses a 16 bit wide signed shift and a mask to
perform what amounts to a 8 bit unsigned shift. So fold the ops
together.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/raid6/recov_neon_inner.c | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid6/recov_neon_inner.c index 7d00c31a6547..f13c07f82297 100644 --- a/lib/raid6/recov_neon_inner.c +++ b/lib/raid6/recov_neon_inner.c @@ -56,14 +56,14 @@ void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp, px = veorq_u8(vld1q_u8(p), vld1q_u8(dp)); vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq)); - vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4); + vy = vshrq_n_u8(vx, 4); vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f)); - vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f)); + vy = vqtbl1q_u8(qm1, vy); qx = veorq_u8(vx, vy); - vy = (uint8x16_t)vshrq_n_s16((int16x8_t)px, 4); + vy = vshrq_n_u8(px, 4); vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f)); - vy = vqtbl1q_u8(pm1, vandq_u8(vy, x0f)); + vy = vqtbl1q_u8(pm1, vy); vx = veorq_u8(vx, vy); db = veorq_u8(vx, qx); @@ -97,9 +97,9 @@ void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq, vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq)); - vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4); + vy = vshrq_n_u8(vx, 4); vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f)); - vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f)); + vy = vqtbl1q_u8(qm1, vy); vx = veorq_u8(vx, vy); vy = veorq_u8(vx, vld1q_u8(p)); |