+
+ smlal \u_dst1\().4s, \u_coef2\().4h, \b\().4h // U += bu * b
(first 4)
+ smlal \v_dst1\().4s, \v_coef2\().4h, \b\().4h // V += bv * b
(first 4)
+ smlal2 \u_dst2\().4s, \u_coef2\().8h, \b\().8h // U += bu * b
(second 4)
+ smlal2 \v_dst2\().4s, \v_coef2\().8h, \b\().8h // V += bv * b
(second 4)
+
+ sqshrn \u_dst\().4h, \u_dst1\().4s, \right_shift // U first 4
pixels
+ sqshrn2 \u_dst\().8h, \u_dst2\().4s, \right_shift // U all 8 pixels
+ sqshrn \v_dst\().4h, \v_dst1\().4s, \right_shift // V first 4
pixels
+ sqshrn2 \v_dst\().8h, \v_dst2\().4s, \right_shift // V all 8 pixels
+.endm
+
.macro rgbToY_neon fmt_bgr, fmt_rgb, element, alpha_first=0
function ff_\fmt_bgr\()ToY_neon, export=1
- cmp w4, #0 // check width > 0
+ cbz w4, 3f // check width > 0
ldp w12, w11, [x5] // w12: ry, w11: gy
ldr w10, [x5, #8] // w10: by
- b.gt 4f
- ret
+ b 4f
endfunc
function ff_\fmt_rgb\()ToY_neon, export=1
- cmp w4, #0 // check width > 0
+ cbz w4, 3f // check width > 0
ldp w10, w11, [x5] // w10: ry, w11: gy
ldr w12, [x5, #8] // w12: by
- b.le 3f
4:
mov w9, #256 // w9 = 1 << (RGB2YUV_SHIFT
- 7)
movk w9, #8, lsl #16 // w9 += 32 <<
(RGB2YUV_SHIFT - 1)
@@ -158,8 +178,7 @@ rgbToY_neon abgr32, argb32, element=4, alpha_first=1
.macro rgbToUV_half_neon fmt_bgr, fmt_rgb, element, alpha_first=0
function ff_\fmt_bgr\()ToUV_half_neon, export=1
- cmp w5, #0 // check width > 0
- b.le 3f
+ cbz w5, 3f // check width > 0
ldp w12, w11, [x6, #12]
ldp w10, w15, [x6, #20]
@@ -168,7 +187,7 @@ function ff_\fmt_bgr\()ToUV_half_neon, export=1
endfunc
function ff_\fmt_rgb\()ToUV_half_neon, export=1
- cmp w5, #0 // check width > 0
+ cmp w5, #0 // check width > 0
b.le 3f
ldp w10, w11, [x6, #12] // w10: ru, w11: gu
@@ -178,32 +197,41 @@ function ff_\fmt_rgb\()ToUV_half_neon, export=1
cmp w5, #8
rgb_set_uv_coeff half=1
b.lt 2f
-1:
+1: // load 16 pixels and prefetch memory for the next block
.if \element == 3
- ld3 { v16.16b, v17.16b, v18.16b }, [x3]
+ ld3 { v16.16b, v17.16b, v18.16b }, [x3], #48
+ prfm pldl1strm, [x3, #48]
.else
- ld4 { v16.16b, v17.16b, v18.16b, v19.16b }, [x3]
+ ld4 { v16.16b, v17.16b, v18.16b, v19.16b }, [x3], #64
+ prfm pldl1strm, [x3, #64]
.endif
+
.if \alpha_first
- uaddlp v21.8h, v19.16b
- uaddlp v20.8h, v18.16b
- uaddlp v19.8h, v17.16b
+ uaddlp v21.8h, v19.16b // v21: summed b pairs
+ uaddlp v20.8h, v18.16b // v20: summed g pairs
+ uaddlp v19.8h, v17.16b // v19: summed r pairs
.else
- uaddlp v19.8h, v16.16b // v19: r
- uaddlp v20.8h, v17.16b // v20: g
- uaddlp v21.8h, v18.16b // v21: b
+ uaddlp v19.8h, v16.16b // v19: summed r pairs
+ uaddlp v20.8h, v17.16b // v20: summed g pairs
+ uaddlp v21.8h, v18.16b // v21: summed b pairs
.endif
- rgb_to_yuv_product v19, v20, v21, v22, v23, v16, v0, v1, v2, #10
- rgb_to_yuv_product v19, v20, v21, v24, v25, v17, v3, v4, v5, #10
- sub w5, w5, #8 // width -= 8
- add x3, x3, #(16*\element)
- cmp w5, #8 // width >= 8 ?
+ mov v22.16b, v6.16b // U first half
+ mov v23.16b, v6.16b // U second half
+ mov v24.16b, v6.16b // V first half
+ mov v25.16b, v6.16b // V second half
+
+ rgb_to_uv_interleaved_product v19, v20, v21, v0, v1, v2, v3, v4,
v5, v22, v23, v24, v25, v16, v17, #10
+
str q16, [x0], #16 // store dst_u
str q17, [x1], #16 // store dst_v
+
+ sub w5, w5, #8 // width -= 8
+ cmp w5, #8 // width >= 8 ?
b.ge 1b
- cbz w5, 3f
-2:
+ cbz w5, 3f // No pixels left? Exit
+
+2: // Scalar fallback for remaining pixels
.if \alpha_first
rgb_load_add_half 1, 5, 2, 6, 3, 7
.else
@@ -213,21 +241,24 @@ function ff_\fmt_rgb\()ToUV_half_neon, export=1
rgb_load_add_half 0, 4, 1, 5, 2, 6
.endif
.endif
-
smaddl x8, w2, w10, x9 // dst_u = ru * r +
const_offset
+ smaddl x16, w2, w13, x9 // dst_v = rv * r +
const_offset (parallel)
+
smaddl x8, w4, w11, x8 // dst_u += gu * g
+ smaddl x16, w4, w14, x16 // dst_v += gv * g
(parallel)
+
smaddl x8, w7, w12, x8 // dst_u += bu * b
- asr x8, x8, #10 // dst_u >>= 10
+ smaddl x16, w7, w15, x16 // dst_v += bv * b
(parallel)
+
+ asr w8, w8, #10 // dst_u >>= 10
+ asr w16, w16, #10 // dst_v >>= 10
+
strh w8, [x0], #2 // store dst_u
-
- smaddl x8, w2, w13, x9 // dst_v = rv * r +
const_offset
- smaddl x8, w4, w14, x8 // dst_v += gv * g
- smaddl x8, w7, w15, x8 // dst_v += bv * b
- asr x8, x8, #10 // dst_v >>= 10
- sub w5, w5, #1
- add x3, x3, #(2*\element)
- strh w8, [x1], #2 // store dst_v
- cbnz w5, 2b
+ strh w16, [x1], #2 // store dst_v
+
+ sub w5, w5, #1 // width--
+ add x3, x3, #(2*\element) // Advance source pointer
+ cbnz w5, 2b // Process next pixel if
any left
3:
ret
endfunc
@@ -244,9 +275,9 @@ function ff_\fmt_bgr\()ToUV_neon, export=1
cmp w5, #0 // check width > 0
b.le 3f
- ldp w12, w11, [x6, #12]
- ldp w10, w15, [x6, #20]
- ldp w14, w13, [x6, #28]
+ ldp w12, w11, [x6, #12] // bu, gu
+ ldp w10, w15, [x6, #20] // ru, bv
+ ldp w14, w13, [x6, #28] // gv, rv
b 4f
endfunc
+ .else // element == 4
+ ld4 { v16.16b, v17.16b, v18.16b, v19.16b }, [x3],
#64
+ prfm pldl1strm, [x3, #64]
+ .endif
+ uxtl v19.8h, v16.8b // v19: r
+ uxtl v20.8h, v17.8b // v20: g
+ uxtl v21.8h, v18.8b // v21: b
+ uxtl2 v22.8h, v16.16b // v22: r
+ uxtl2 v23.8h, v17.16b // v23: g
+ uxtl2 v24.8h, v18.16b // v24: b
.endif
- rgb_to_yuv_product v19, v20, v21, v25, v26, v16, v0, v1, v2, #9
- rgb_to_yuv_product v22, v23, v24, v27, v28, v17, v0, v1, v2, #9
- rgb_to_yuv_product v19, v20, v21, v25, v26, v18, v3, v4, v5, #9
- rgb_to_yuv_product v22, v23, v24, v27, v28, v19, v3, v4, v5, #9
- sub w5, w5, #16
- add x3, x3, #(16*\element)
- cmp w5, #16
- stp q16, q17, [x0], #32 // store to dst_u
- stp q18, q19, [x1], #32 // store to dst_v
+ // process 2 groups of 8 pixels
+ mov v25.16b, v6.16b // U_dst1 = const_offset
(32-bit accumulators)
+ mov v26.16b, v6.16b // U_dst2 = const_offset
+ mov v27.16b, v6.16b // V_dst1 = const_offset
+ mov v28.16b, v6.16b // V_dst2 = const_offset
+ rgb_to_uv_interleaved_product v19, v20, v21, v0, v1, v2, v3, v4,
v5, v25, v26, v27, v28, v16, v18, #9
+
+ mov v25.16b, v6.16b
+ mov v26.16b, v6.16b
+ mov v27.16b, v6.16b
+ mov v28.16b, v6.16b
+ rgb_to_uv_interleaved_product v22, v23, v24, v0, v1, v2, v3, v4,
v5, v25, v26, v27, v28, v17, v19, #9
+
+ sub w5, w5, #16 // width -= 16
+ cmp w5, #16 // width >= 16 ?
+ stp q16, q17, [x0], #32 // store to dst_u
(post-increment)
+ stp q18, q19, [x1], #32 // store to dst_v
(post-increment)
b.ge 1b
- cbz w5, 3f
+ cbz w5, 3f // No pixels left? Exit
+
2:
.if \alpha_first
ldrb w16, [x3, #1] // w16: r
@@ -292,13 +350,13 @@ function ff_\fmt_rgb\()ToUV_neon, export=1
smaddl x8, w16, w10, x9 // x8 = ru * r +
const_offset
smaddl x8, w17, w11, x8 // x8 += gu * g
smaddl x8, w4, w12, x8 // x8 += bu * b
- asr w8, w8, #9 // x8 >>= 9
+ asr x8, x8, #9 // x8 >>= 9
strh w8, [x0], #2 // store to dst_u
