diff --git a/source/rotate_neon64.cc b/source/rotate_neon64.cc index 1c95b554f..5844c0d28 100644 --- a/source/rotate_neon64.cc +++ b/source/rotate_neon64.cc @@ -253,7 +253,9 @@ void TransposeWx4_32_NEON(const uint8_t* src, // Main loop transpose 4x4. Read a column, write a row. "1: \n" - "ld4 {v0.s, v1.s, v2.s, v3.s}[0], [%0], %9 \n" + "ldp s0, s1, [%0] \n" + "ldp s2, s3, [%0, #8] \n" + "add %0, %0, %9 \n" "ld4 {v0.s, v1.s, v2.s, v3.s}[1], [%1], %9 \n" "ld4 {v0.s, v1.s, v2.s, v3.s}[2], [%2], %9 \n" "ld4 {v0.s, v1.s, v2.s, v3.s}[3], [%3], %9 \n"