Skip to content

Commit

Permalink
Use int16 min/max for _mm_set_epi16() calls (#395)
Browse files Browse the repository at this point in the history 
* Use int16 min/max for _mm_set_epi16() calls

This fixes a bug that causes g0 overflows when compiled on Intel processors and run on AMD Ryzen processors.

According to Intel, the `_mm_set_epi16()` function takes signed shorts (int16): https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=mm_set_epi16&ig_expand=6355,6355

But 0-65535 is the range of uint16, not int16; causing an overflow to -1. This is warned of by the compiler: `implict conversion from int to short changes value from 65535 to -1`

For whatever reason, compiling and running on AMD Ryzen chip succeeded fine. Compiling and runing on an Intel chip also worked fine. But compiling on Intel and running on AMD caused an exception.

Using the int16 range fixes the problem. However, this is not my skill set and I am not sure if this is the right fix. Please verify. Thank you!

* Update sse-motion.cc: _mm_set_epi16 use 0, -1
  • Loading branch information
@mholt
mholt authored Nov 13, 2024
1 parent 336272b commit 62a8ae5
Showing 1 changed file with 18 additions and 18 deletions.
36 changes: 18 additions & 18 deletions libde265/x86/sse-motion.cc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3527,9 +3527,9 @@ void ff_hevc_put_hevc_qpel_h_1_v_1_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -3710,9 +3710,9 @@ void ff_hevc_put_hevc_qpel_h_1_v_2_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -3887,9 +3887,9 @@ void ff_hevc_put_hevc_qpel_h_1_v_3_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -4058,9 +4058,9 @@ void ff_hevc_put_hevc_qpel_h_2_v_1_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -4241,9 +4241,9 @@ void ff_hevc_put_hevc_qpel_h_2_v_2_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -4419,9 +4419,9 @@ void ff_hevc_put_hevc_qpel_h_2_v_3_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -4592,9 +4592,9 @@ void ff_hevc_put_hevc_qpel_h_3_v_1_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -4778,9 +4778,9 @@ void ff_hevc_put_hevc_qpel_h_3_v_2_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down Expand Up @@ -4958,9 +4958,9 @@ void ff_hevc_put_hevc_qpel_h_3_v_3_sse(int16_t *dst, ptrdiff_t dststride,
r0 = _mm_srli_epi32(r0, 6);

r1 = _mm_and_si128(r1,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_and_si128(r0,
_mm_set_epi16(0, 65535, 0, 65535, 0, 65535, 0, 65535));
_mm_set_epi16(0, -1, 0, -1, 0, -1, 0, -1));
r0 = _mm_hadd_epi16(r0, r1);
_mm_store_si128((__m128i *) &dst[x], r0);

Expand Down

0 comments on commit 62a8ae5

Please sign in to comment.