[opus] [AArch64 neon intrinsics v4 5/5] Add Neon fixed-point implementation of xcorr_kernel.

[Jonathan Lennox]

Used for celt_pitch_xcorr on aarch64, and celt_fir and celt_iir on both armv7 and aarch64.
---
 celt/arm/arm_celt_map.c   | 17 +++++++++++++
 celt/arm/celt_neon_intr.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++-
 celt/arm/pitch_arm.h      | 31 +++++++++++++++++++++++-
 3 files changed, 107 insertions(+), 2 deletions(-)

diff --git a/celt/arm/arm_celt_map.c b/celt/arm/arm_celt_map.c
index 85a48e8..0d002b9 100644
--- a/celt/arm/arm_celt_map.c
+++ b/celt/arm/arm_celt_map.c
@@ -60,6 +60,23 @@ void (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *,
 #  endif
 # endif /* FIXED_POINT */
 
+#if defined(FIXED_POINT) && defined(OPUS_HAVE_RTCD) && \
+	defined(OPUS_ARM_MAY_HAVE_NEON_INTR) && !defined(OPUS_ARM_PRESUME_NEON_INTR)
+
+void (*const XCORR_KERNEL_IMPL[OPUS_ARCHMASK + 1])(
+         const opus_val16 *x,
+         const opus_val16 *y,
+         opus_val32       sum[4],
+         int              len
+) = {
+  xcorr_kernel_c,                /* ARMv4 */
+  xcorr_kernel_c,                /* EDSP */
+  xcorr_kernel_c,                /* Media */
+  xcorr_kernel_neon_fixed,       /* Neon */
+};
+
+#endif
+
 # if defined(OPUS_ARM_MAY_HAVE_NEON_INTR)
 #  if defined(HAVE_ARM_NE10)
 #   if defined(CUSTOM_MODES)
diff --git a/celt/arm/celt_neon_intr.c b/celt/arm/celt_neon_intr.c
index 47dce15..e721418 100644
--- a/celt/arm/celt_neon_intr.c
+++ b/celt/arm/celt_neon_intr.c
@@ -37,7 +37,66 @@
 #include <arm_neon.h>
 #include "../pitch.h"
 
-#if !defined(FIXED_POINT)
+#if defined(FIXED_POINT)
+void xcorr_kernel_neon_fixed(const opus_val16 * x, const opus_val16 * y, opus_val32 sum[4], int len)
+{
+	int j;
+	int32x4_t a = vld1q_s32(sum);
+	/* Load y[0...3] */
+	/* This requires len>0 to always be valid (which we assert in the C code). */
+	int16x4_t y0 = vld1_s16(y);
+	y += 4;
+
+	for (j = 0; j + 8 <= len; j += 8)
+	{
+		/* Load x[0...7] */
+		int16x8_t xx = vld1q_s16(x);
+		int16x4_t x0 = vget_low_s16(xx);
+		int16x4_t x4 = vget_high_s16(xx);
+		/* Load y[4...11] */
+		int16x8_t yy = vld1q_s16(y);
+		int16x4_t y4 = vget_low_s16(yy);
+		int16x4_t y8 = vget_high_s16(yy);
+		int32x4_t a0 = vmlal_lane_s16(a, y0, x0, 0);
+		int32x4_t a1 = vmlal_lane_s16(a0, y4, x4, 0);
+
+		int16x4_t y1 = vext_s16(y0, y4, 1);
+		int16x4_t y5 = vext_s16(y4, y8, 1);
+		int32x4_t a2 = vmlal_lane_s16(a1, y1, x0, 1);
+		int32x4_t a3 = vmlal_lane_s16(a2, y5, x4, 1);
+
+		int16x4_t y2 = vext_s16(y0, y4, 2);
+		int16x4_t y6 = vext_s16(y4, y8, 2);
+		int32x4_t a4 = vmlal_lane_s16(a3, y2, x0, 2);
+		int32x4_t a5 = vmlal_lane_s16(a4, y6, x4, 2);
+
+		int16x4_t y3 = vext_s16(y0, y4, 3);
+		int16x4_t y7 = vext_s16(y4, y8, 3);
+		int32x4_t a6 = vmlal_lane_s16(a5, y3, x0, 3);
+		int32x4_t a7 = vmlal_lane_s16(a6, y7, x4, 3);
+
+		y0 = y8;
+		a = a7;
+		x += 8;
+		y += 8;
+	}
+
+	for (; j < len; j++)
+	{
+		int16x4_t x0 = vld1_dup_s16(x);  /* load next x */
+		int32x4_t a0 = vmlal_s16(a, y0, x0);
+
+		int16x4_t y4 = vld1_dup_s16(y);  /* load next y */
+		y0 = vext_s16(y0, y4, 1);
+		a = a0;
+		x++;
+		y++;
+	}
+
+	vst1q_s32(sum, a);
+}
+
+#else
 /*
  * Function: xcorr_kernel_neon_float
  * ---------------------------------
diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h
index 2264f71..6f4e2b6 100644
--- a/celt/arm/pitch_arm.h
+++ b/celt/arm/pitch_arm.h
@@ -64,7 +64,36 @@ extern opus_val32
 #   define OVERRIDE_PITCH_XCORR (1)
 #   define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \
   ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(_x, _y, xcorr, len, max_pitch))
-#  endif
+
+#endif
+
+#  if defined(OPUS_ARM_MAY_HAVE_NEON_INTR)
+
+void xcorr_kernel_neon_fixed(
+                    const opus_val16 *x,
+                    const opus_val16 *y,
+                    opus_val32       sum[4],
+                    int              len);
+
+#   define OVERRIDE_XCORR_KERNEL (1)
+
+#   if defined(OPUS_ARM_PRESUME_NEON_INTR) || !defined(OPUS_HAVE_RTCD)
+#define xcorr_kernel(x, y, sum, len, arch) \
+    ((void)arch, xcorr_kernel_neon_fixed(x, y, sum, len))
+#   else /* Start !OPUS_ARM_PRESUME_NEON_INTR */
+
+extern void (*const XCORR_KERNEL_IMPL[OPUS_ARCHMASK + 1])(
+                    const opus_val16 *x,
+                    const opus_val16 *y,
+                    opus_val32       sum[4],
+                    int              len);
+
+#define xcorr_kernel(x, y, sum, len, arch) \
+    ((*XCORR_KERNEL_IMPL[(arch) & OPUS_ARCHMASK])(x, y, sum, len))
+
+
+#   endif /* end !OPUS_ARM_PRESUME_NEON_INTR */
+#  endif /* end OPUS_ARM_MAY_HAVE_NEON_INTR */
 
 #else /* Start !FIXED_POINT */
 /* Float case */
-- 
2.5.4 (Apple Git-61)