在 ARMv7a 上与 Neon 进行 64 位签名比较支持 CMGT 的最有效方法是什么? [英] What is the most efficient way to support CMGT with 64bit signed comparisons on ARMv7a with Neon?

问题描述

这个问题最初是为 这里是 SSE2.由于每个算法都与 ARMv7a+NEON 对相同操作的支持重叠，因此更新了问题以包括 ARMv7+NEON 版本.应评论者的要求，在此处提出此问题以表明它确实是一个单独的主题，并提供可能对 ARMv7+NEON 更实用的替代解决方案.这些问题的最终目的是找到考虑到 WebAssembly SIMD 的理想实现.

This question was originally posed for SSE2 here. Since every single algorithm overlapped with ARMv7a+NEON's support for the same operations, the question was updated to include the ARMv7+NEON versions. At the request of a commenter, this question is asked here to show that it is indeed a separate topic and to provide alternative solutions that might be more practical for ARMv7+NEON. The net purpose of these questions is to find ideal implementations for consideration into WebAssembly SIMD.

推荐答案

有符号 64 位饱和减法.

Signed 64-bit saturating subtract.

假设我使用 _mm_subs_epi16 的测试是正确的，并转换为 1:1 到 NEON...

Assuming my tests using _mm_subs_epi16 are correct and translate to 1:1 to NEON...

uint64x2_t pcmpgtq_armv7 (int64x2_t a, int64x2_t b) {
    return vreinterpretq_u64_s64(vshrq_n_s64(vqsubq_s64(b, a), 63));
}

这肯定是模拟 pcmpgtq 的最快可行方法.

Would certainly seem to be the fastest achievable way to emulate pcmpgtq.

黑客之乐给出以下公式:

// return (a > b) ? -1LL : 0LL; 
int64_t cmpgt(int64_t a, int64_t b) {
    return ((b & ~a) | ((b - a) & ~(b ^ a))) >> 63; 
}

int64_t cmpgt(int64_t a, int64_t b) {
    return ((b - a) ^ ((b ^ a) & ((b - a) ^ b))) >> 63;
}

这篇关于在 ARMv7a 上与 Neon 进行 64 位签名比较支持 CMGT 的最有效方法是什么?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！