Skip to content

SSE2: keep i32 multiply products in place #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Auburn merged 1 commit into from
Oct 17, 2026
Merged

SSE2: keep i32 multiply products in place #16

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions include/FastSIMD/ToolSet/x86/128/i32x4.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,9 +44,11 @@ namespace FS
}
else
{
// Products stay in place in their 64 bit lanes: chained multiplies need no repacking in between,
// pmuludq only reads the low 32 bits of each 64 bit lane, which the and/shift/or leave in place
__m128i mul20 = _mm_mul_epu32( native, rhs.native ); /* mul 2,0*/
__m128i mul31 = _mm_mul_epu32( _mm_srli_si128( native, 4 ), _mm_srli_si128( rhs.native, 4 ) ); /* mul 3,1 */
native = _mm_unpacklo_epi32( _mm_shuffle_epi32( mul20, _MM_SHUFFLE( 0, 0, 2, 0 ) ), _mm_shuffle_epi32( mul31, _MM_SHUFFLE( 0, 0, 2, 0 ) ) ); /* shuffle results to [63..0] and pack */
__m128i mul31 = _mm_mul_epu32( _mm_shuffle_epi32( native, _MM_SHUFFLE( 3, 3, 1, 1 ) ), _mm_shuffle_epi32( rhs.native, _MM_SHUFFLE( 3, 3, 1, 1 ) ) ); /* mul 3,1 */
native = _mm_or_si128( _mm_and_si128( mul20, _mm_set_epi32( 0, -1, 0, -1 ) ), _mm_slli_epi64( mul31, 32 ) );
}
return *this;
}
Expand Down
Loading