2322e3bcf7
Prefetches scratchpad data as soon as possible to calculate data address for the next load. Up to ~1.4% speedup on Ryzen 7 3700X @ 4.1 GHz, RAM 3200 MHz 14-14-14-28 with optimized sub-timings: Variant|Before H/S|After H/S -------|----------|--------- rx/0|8663|8777 rx/wow|9867|10009 rx/loki|8652|8731
28 lines
716 B
PHP
28 lines
716 B
PHP
lea rcx, [rsi+rax]
|
|
push rcx
|
|
xor r8, qword ptr [rcx+0]
|
|
xor r9, qword ptr [rcx+8]
|
|
xor r10, qword ptr [rcx+16]
|
|
xor r11, qword ptr [rcx+24]
|
|
xor r12, qword ptr [rcx+32]
|
|
xor r13, qword ptr [rcx+40]
|
|
xor r14, qword ptr [rcx+48]
|
|
xor r15, qword ptr [rcx+56]
|
|
lea rcx, [rsi+rdx]
|
|
push rcx
|
|
cvtdq2pd xmm0, qword ptr [rcx+0]
|
|
cvtdq2pd xmm1, qword ptr [rcx+8]
|
|
cvtdq2pd xmm2, qword ptr [rcx+16]
|
|
cvtdq2pd xmm3, qword ptr [rcx+24]
|
|
cvtdq2pd xmm4, qword ptr [rcx+32]
|
|
cvtdq2pd xmm5, qword ptr [rcx+40]
|
|
cvtdq2pd xmm6, qword ptr [rcx+48]
|
|
cvtdq2pd xmm7, qword ptr [rcx+56]
|
|
andps xmm4, xmm13
|
|
andps xmm5, xmm13
|
|
andps xmm6, xmm13
|
|
andps xmm7, xmm13
|
|
orps xmm4, xmm14
|
|
orps xmm5, xmm14
|
|
orps xmm6, xmm14
|
|
orps xmm7, xmm14
|