+def generate_sse2():
+ print '''
+#if defined(PIPE_ARCH_SSE)
+
+#include "util/u_sse.h"
+
+static ALWAYS_INLINE void
+swz4( const __m128i * restrict x,
+ const __m128i * restrict y,
+ const __m128i * restrict z,
+ const __m128i * restrict w,
+ __m128i * restrict a,
+ __m128i * restrict b,
+ __m128i * restrict c,
+ __m128i * restrict d)
+{
+ __m128i i, j, k, l;
+ __m128i m, n, o, p;
+ __m128i e, f, g, h;
+
+ m = _mm_unpacklo_epi8(*x,*y);
+ n = _mm_unpackhi_epi8(*x,*y);
+ o = _mm_unpacklo_epi8(*z,*w);
+ p = _mm_unpackhi_epi8(*z,*w);
+
+ i = _mm_unpacklo_epi16(m,n);
+ j = _mm_unpackhi_epi16(m,n);
+ k = _mm_unpacklo_epi16(o,p);
+ l = _mm_unpackhi_epi16(o,p);
+
+ e = _mm_unpacklo_epi8(i,j);
+ f = _mm_unpackhi_epi8(i,j);
+ g = _mm_unpacklo_epi8(k,l);
+ h = _mm_unpackhi_epi8(k,l);
+
+ *a = _mm_unpacklo_epi64(e,g);
+ *b = _mm_unpackhi_epi64(e,g);
+ *c = _mm_unpacklo_epi64(f,h);
+ *d = _mm_unpackhi_epi64(f,h);
+}
+
+static ALWAYS_INLINE void
+unswz4( const __m128i * restrict a,
+ const __m128i * restrict b,
+ const __m128i * restrict c,
+ const __m128i * restrict d,
+ __m128i * restrict x,
+ __m128i * restrict y,
+ __m128i * restrict z,
+ __m128i * restrict w)
+{
+ __m128i i, j, k, l;
+ __m128i m, n, o, p;
+
+ i = _mm_unpacklo_epi8(*a,*b);
+ j = _mm_unpackhi_epi8(*a,*b);
+ k = _mm_unpacklo_epi8(*c,*d);
+ l = _mm_unpackhi_epi8(*c,*d);
+
+ m = _mm_unpacklo_epi16(i,k);
+ n = _mm_unpackhi_epi16(i,k);
+ o = _mm_unpacklo_epi16(j,l);
+ p = _mm_unpackhi_epi16(j,l);
+
+ *x = _mm_unpacklo_epi64(m,n);
+ *y = _mm_unpackhi_epi64(m,n);
+ *z = _mm_unpacklo_epi64(o,p);
+ *w = _mm_unpackhi_epi64(o,p);
+}
+
+static void
+lp_tile_b8g8r8a8_unorm_swizzle_4ub_sse2(uint8_t * restrict dst,
+ const uint8_t * restrict src, unsigned src_stride,
+ unsigned x0, unsigned y0)
+{
+ __m128i *dst128 = (__m128i *) dst;
+ unsigned x, y;
+
+ src += y0 * src_stride;
+ src += x0 * sizeof(uint32_t);
+
+ for (y = 0; y < TILE_SIZE; y += 4) {
+ const uint8_t *src_row = src;
+
+ for (x = 0; x < TILE_SIZE; x += 4) {
+ swz4((const __m128i *) (src_row + 0 * src_stride),
+ (const __m128i *) (src_row + 1 * src_stride),
+ (const __m128i *) (src_row + 2 * src_stride),
+ (const __m128i *) (src_row + 3 * src_stride),
+ dst128 + 2, /* b */
+ dst128 + 1, /* g */
+ dst128 + 0, /* r */
+ dst128 + 3); /* a */
+
+ dst128 += 4;
+ src_row += sizeof(__m128i);
+ }
+
+ src += 4 * src_stride;
+ }
+}
+
+static void
+lp_tile_b8g8r8a8_unorm_unswizzle_4ub_sse2(const uint8_t * restrict src,
+ uint8_t * restrict dst, unsigned dst_stride,
+ unsigned x0, unsigned y0)
+{
+ unsigned int x, y;
+ const __m128i *src128 = (const __m128i *) src;
+
+ dst += y0 * dst_stride;
+ dst += x0 * sizeof(uint32_t);
+
+ for (y = 0; y < TILE_SIZE; y += 4) {
+ const uint8_t *dst_row = dst;
+
+ for (x = 0; x < TILE_SIZE; x += 4) {
+ unswz4( &src128[2], /* b */
+ &src128[1], /* g */
+ &src128[0], /* r */
+ &src128[3], /* a */
+ (__m128i *) (dst_row + 0 * dst_stride),
+ (__m128i *) (dst_row + 1 * dst_stride),
+ (__m128i *) (dst_row + 2 * dst_stride),
+ (__m128i *) (dst_row + 3 * dst_stride));
+
+ src128 += 4;
+ dst_row += sizeof(__m128i);;
+ }
+
+ dst += 4 * dst_stride;
+ }
+}
+
+static void
+lp_tile_b8g8r8x8_unorm_swizzle_4ub_sse2(uint8_t * restrict dst,
+ const uint8_t * restrict src, unsigned src_stride,
+ unsigned x0, unsigned y0)
+{
+ __m128i *dst128 = (__m128i *) dst;
+ unsigned x, y;
+
+ src += y0 * src_stride;
+ src += x0 * sizeof(uint32_t);
+
+ for (y = 0; y < TILE_SIZE; y += 4) {
+ const uint8_t *src_row = src;
+
+ for (x = 0; x < TILE_SIZE; x += 4) {
+ swz4((const __m128i *) (src_row + 0 * src_stride),
+ (const __m128i *) (src_row + 1 * src_stride),
+ (const __m128i *) (src_row + 2 * src_stride),
+ (const __m128i *) (src_row + 3 * src_stride),
+ dst128 + 2, /* b */
+ dst128 + 1, /* g */
+ dst128 + 0, /* r */
+ dst128 + 3); /* a */
+
+ dst128 += 4;
+ src_row += sizeof(__m128i);
+ }
+
+ src += 4 * src_stride;
+ }
+}
+
+static void
+lp_tile_b8g8r8x8_unorm_unswizzle_4ub_sse2(const uint8_t * restrict src,
+ uint8_t * restrict dst, unsigned dst_stride,
+ unsigned x0, unsigned y0)
+{
+ unsigned int x, y;
+ const __m128i *src128 = (const __m128i *) src;
+
+ dst += y0 * dst_stride;
+ dst += x0 * sizeof(uint32_t);
+
+ for (y = 0; y < TILE_SIZE; y += 4) {
+ const uint8_t *dst_row = dst;
+
+ for (x = 0; x < TILE_SIZE; x += 4) {
+ unswz4( &src128[2], /* b */
+ &src128[1], /* g */
+ &src128[0], /* r */
+ &src128[3], /* a */
+ (__m128i *) (dst_row + 0 * dst_stride),
+ (__m128i *) (dst_row + 1 * dst_stride),
+ (__m128i *) (dst_row + 2 * dst_stride),
+ (__m128i *) (dst_row + 3 * dst_stride));
+
+ src128 += 4;
+ dst_row += sizeof(__m128i);;
+ }
+
+ dst += 4 * dst_stride;
+ }
+}
+
+#endif /* PIPE_ARCH_SSE */
+'''
+
+