libswscale: Enable hscale_avx2 for all input sizes.

ff_shuffle_filter_coefficients shuffles the tail as required.

Signed-off-by: Anton Khirnov <anton@khirnov.net>

libswscale/utils.c

@@ -268,8 +268,7 @@ int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos,
 #if ARCH_X86_64
     int i, j, k;
     int cpu_flags = av_get_cpu_flags();
-    // avx2 hscale filter processes 16 pixel blocks.
-    if (!filter || dstW % 16 != 0)
+    if (!filter)
         return 0;
     if (EXTERNAL_AVX2_FAST(cpu_flags) && !(cpu_flags & AV_CPU_FLAG_SLOW_GATHER)) {
         if ((c->srcBpc == 8) && (c->dstBpc <= 14)) {
@@ -281,9 +280,11 @@ int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos,
            }
            // Do not swap filterPos for pixels which won't be processed by
            // the main loop.
-           for (i = 0; i + 8 <= dstW; i += 8) {
+           for (i = 0; i + 16 <= dstW; i += 16) {
                FFSWAP(int, filterPos[i + 2], filterPos[i + 4]);
                FFSWAP(int, filterPos[i + 3], filterPos[i + 5]);
+               FFSWAP(int, filterPos[i + 10], filterPos[i + 12]);
+               FFSWAP(int, filterPos[i + 11], filterPos[i + 13]);
            }
            if (filterSize > 4) {
                // 16 pixels are processed at a time.
@@ -297,6 +298,18 @@ int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos,
                        }
                    }
                }
+               // 4 pixels are processed at a time in the tail.
+               for (; i < dstW; i += 4) {
+                   // 4 filter coeffs are processed at a time.
+                   int rem = dstW - i >= 4 ? 4 : dstW - i;
+                   for (k = 0; k + 4 <= filterSize; k += 4) {
+                       for (j = 0; j < rem; ++j) {
+                           int from = (i + j) * filterSize + k;
+                           int to = i * filterSize + j * 4 + k * 4;
+                           memcpy(&filter[to], &filterCopy[from], 4 * sizeof(int16_t));
+                       }
+                   }
+               }
            }
            av_free(filterCopy);
         }

libswscale/x86/swscale.c

@@ -625,9 +625,7 @@ switch(c->dstBpc){ \
 
     if (EXTERNAL_AVX2_FAST(cpu_flags) && !(cpu_flags & AV_CPU_FLAG_SLOW_GATHER)) {
         if ((c->srcBpc == 8) && (c->dstBpc <= 14)) {
-            if (c->chrDstW % 16 == 0)
             ASSIGN_AVX2_SCALE_FUNC(c->hcScale, c->hChrFilterSize);
-            if (c->dstW % 16 == 0)
             ASSIGN_AVX2_SCALE_FUNC(c->hyScale, c->hLumFilterSize);
         }
     }

tests/checkasm/sw_scale.c

@@ -329,7 +329,7 @@ static void check_hscale(void)
                 ff_sws_init_scale(ctx);
                 memcpy(filterAvx2, filter, sizeof(uint16_t) * (SRC_PIXELS * MAX_FILTER_WIDTH + MAX_FILTER_WIDTH));
                 if ((cpu_flags & AV_CPU_FLAG_AVX2) && !(cpu_flags & AV_CPU_FLAG_SLOW_GATHER))
-                    ff_shuffle_filter_coefficients(ctx, filterPosAvx, width, filterAvx2, SRC_PIXELS);
+                    ff_shuffle_filter_coefficients(ctx, filterPosAvx, width, filterAvx2, ctx->dstW);
 
                 if (check_func(ctx->hcScale, "hscale_%d_to_%d__fs_%d_dstW_%d", ctx->srcBpc, ctx->dstBpc + 1, width, ctx->dstW)) {
                     memset(dst0, 0, SRC_PIXELS * sizeof(dst0[0]));