U++ framework
Do not panic. Ask here before giving up.

Home » Developing U++ » U++ Developers corner » SSE2 and SVO optimization (Painter, memcpy....)
Re: BufferPainter::Clear() optimization [message #53957 is a reply to message #53953] Sun, 17 May 2020 23:25 Go to previous messageGo to previous message
Tom1
Messages: 1319
Registered: March 2007
Ultimate Contributor
Mirek,

Please check out this one. It features better performance on MSBT19 / MSBT19x64 with low counts, and works well on CLANG/CLANGx64 too:
inline void new_memset128(void *b, dword data, int len){
	
	switch(len){
		case 4: ((dword *)b)[3] = data;
		case 3: ((dword *)b)[2] = data;
		case 2: ((dword *)b)[1] = data;
		case 1: ((dword *)b)[0] = data;
		case 0: return;
	}
	
	__m128i q = _mm_set1_epi32(*(int*)&data);
	__m128i *w = (__m128i*)b;
	
	switch(len>>2){
		default:{
			__m128i *e = (__m128i*)b + (len>>2) - 4;
			if(len <= 2*1024*1024){
				while(w<e){
					_mm_storeu_si128(w++, q);
					_mm_storeu_si128(w++, q);
					_mm_storeu_si128(w++, q);
					_mm_storeu_si128(w++, q);
				}
			}
			else{
				while(w<e){
					_mm_stream_si128(w++, q);
					_mm_stream_si128(w++, q);
					_mm_stream_si128(w++, q);
					_mm_stream_si128(w++, q);
				}
			}
		}
		case 4: _mm_storeu_si128(w++, q);
		case 3: _mm_storeu_si128(w++, q);
		case 2: _mm_storeu_si128(w++, q);
		case 1: _mm_storeu_si128(w++, q);
	}
	switch(len&3){
		case 3: ((dword *)b)[len-3] = data;
		case 2: ((dword *)b)[len-2] = data;
		case 1: ((dword *)b)[len-1] = data;
	}
}



Best regards,

Tom

EDIT: Fine tuning...

[Updated on: Sun, 17 May 2020 23:55]

Report message to a moderator

 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: Should we still care about big-endian CPUs?
Next Topic: TheIDE crash after switching package
Goto Forum:
  


Current Time: Wed May 13 02:24:28 GMT+2 2026

Total time taken to generate the page: 0.01873 seconds