Corrected optimization of 8x8 DCT code

The 8x8 DCT uses a fast version whenever possible.
There was a mistake in the checking code which
meant sometimes the fast version was used when it
was not safe to do so.

Change-Id: I154c84c9e2d836764768a11082947ca30f4b5ab7
(cherry picked from commit fd05fb0c21e253b4d6f92d7e0b752850ff8ab188)

diff --git a/vp9/common/x86/vp9_idct_intrin_sse2.c b/vp9/common/x86/vp9_idct_intrin_sse2.c
index 3610c716504f408668ad34de6434c8f10e8cd81f..42e0baa05b442bf5d0a4e3d717009b9b45671670 100644 (file)
--- a/vp9/common/x86/vp9_idct_intrin_sse2.c
+++ b/vp9/common/x86/vp9_idct_intrin_sse2.c
@@ -4260,7 +4260,7 @@ void vp9_highbd_idct8x8_10_add_sse2(const tran_low_t *input, uint8_t *dest8,
     // N.B. Only first 4 cols contain non-zero coeffs
     max_input = _mm_max_epi16(inptr[0], inptr[1]);
     min_input = _mm_min_epi16(inptr[0], inptr[1]);
-    for (i = 2; i < 4; i++) {
+    for (i = 2; i < 8; i++) {
       max_input = _mm_max_epi16(max_input, inptr[i]);
       min_input = _mm_min_epi16(min_input, inptr[i]);
     }