RandomX: rewrote dataset read code

Unified code for AMD and Intel
1% faster on Intel
0.15% faster on AMD Ryzen

src/crypto/randomx/asm/program_prologue_linux.inc

@@ -22,6 +22,7 @@
 	mov rsi, rdx                ;# uint8_t* scratchpad
 
 	mov rax, rbp
+	ror rbp, 32
 
 	;# zero integer registers
 	xor r8, r8