__lasx_xvsllwil_d_w

LASX intrinsic · group: Shift

Synopsis

__m256i __lasx_xvsllwil_d_w (__m256i a, imm0_31 imm)
#include <lasxintrin.h>
Instruction: xvsllwil.d.w xr, xr, imm
CPU Flags: LASX

Description

For each 128-bit lane, sign-extend and shift the 32-bit elements in the lower part of that lane by imm to 64-bit result.

Operation

for (int i = 0; i < 2; i++) {
  dst.dword[i] = (s64)(s32)a.word[i] << imm;
}
for (int i = 2; i < 4; i++) {
  dst.dword[i] = (s64)(s32)a.word[i + 2] << imm;
}

// Expands to:

if (0) {
  dst.dword[0] = ((s64)((s32)a.word[0])) << imm;
  dst.dword[1] = ((s64)((s32)a.word[1])) << imm;
  dst.dword[2] = ((s64)((s32)a.word[4])) << imm;
  dst.dword[3] = ((s64)((s32)a.word[5])) << imm;
}

Tested on real machine.

Latency and Throughput

CPU	µarch	Latency	Throughput (IPC)
3C5000	LA464	2	1
3A6000	LA664	2	2
3C6000	LA664	2	2

---

All intrinsics in alphabetical order