Closed zhangfrank closed 4 years ago
No, that one hasn't been implemented yet. I'll add it to my todo list.
Good, thank you! Frank
From: John W. Ratcliff [mailto:notifications@github.com] Sent: 2017年3月22日 1:22 To: jratcliff63367/sse2neon sse2neon@noreply.github.com Cc: b49159@freescale.com; Author author@noreply.github.com Subject: Re: [jratcliff63367/sse2neon] How to convert _mm_madd_epi16 to neon instructions (#5)
No, that one hasn't been implemented yet. I'll add it to my todo list.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHubhttps://github.com/jratcliff63367/sse2neon/issues/5#issuecomment-288153457, or mute the threadhttps://github.com/notifications/unsubscribe-auth/APRUaB9Hfh5YNw03mHS2KNqBYqoEMtqFks5roAc5gaJpZM4Go_uX.
int32x4_t pl = vmull_s16(vget_low_s16(a), vget_low_s16(b));
int32x4_t ph = vmull_s16(vget_high_s16(a), vget_high_s16(b));
int32x2_t rl = vpadd_s32(vget_low_s32(pl), vget_high_s32(pl));
int32x2_t rh = vpadd_s32(vget_low_s32(ph), vget_high_s32(ph));
int32x4_t result = vcombine_s32(rl, rh);
AArch64 would make things a bit easier, I think.
Implemented in DLTcollab/sse2neon.
Hi, Thank you for your work to convert SSE instructions to NEON! Do you know how to convert _mm_madd_epi16 to neon instructions? Many thanks!
Best Regards,
Frank