Light JIT compiler - Linux

src/JitCompilerX86-static.S

@@ -31,8 +31,10 @@
 .global DECL(randomx_program_loop_load)
 .global DECL(randomx_program_start)
 .global DECL(randomx_program_read_dataset)
+.global DECL(randomx_program_read_dataset_light)
 .global DECL(randomx_program_loop_store)
 .global DECL(randomx_program_loop_end)
+.global DECL(randomx_program_read_dataset_light_sub)
 .global DECL(randomx_program_epilogue)
 .global DECL(randomx_program_end)
 
@@ -58,12 +60,21 @@ DECL(randomx_program_start):
 DECL(randomx_program_read_dataset):
 	#include "asm/program_read_dataset.inc"
 
+DECL(randomx_program_read_dataset_light):
+	#include "asm/program_read_dataset_light.inc"
+
 DECL(randomx_program_loop_store):
 	#include "asm/program_loop_store.inc"
 
 DECL(randomx_program_loop_end):
 	nop
 
+.balign 64
+DECL(randomx_program_read_dataset_light_sub):
+	#include "asm/program_read_dataset_light_sub.inc"
+squareHashSub:
+	#include "asm/squareHash.inc"
+
 .balign 64
 DECL(randomx_program_epilogue):
 	#include "asm/program_epilogue_linux.inc"

src/asm/program_transform_address.inc

@@ -1,154 +0,0 @@
-	;# 90 address transformations
-	;# forced REX prefix is used to make all transformations 4 bytes long
-	lea eax, [rax+rax*8+109]
-	db 64
-	xor eax, 96
-	lea eax, [rax+rax*8-19]
-	db 64
-	add eax, -98
-	db 64
-	add eax, -21
-	db 64
-	xor eax, -80
-	lea eax, [rax+rax*8-92]
-	db 64
-	add eax, 113
-	lea eax, [rax+rax*8+100]
-	db 64
-	add eax, -39
-	db 64
-	xor eax, 120
-	lea eax, [rax+rax*8-119]
-	db 64
-	add eax, -113
-	db 64
-	add eax, 111
-	db 64
-	xor eax, 104
-	lea eax, [rax+rax*8-83]
-	lea eax, [rax+rax*8+127]
-	db 64
-	xor eax, -112
-	db 64
-	add eax, 89
-	db 64
-	add eax, -32
-	db 64
-	add eax, 104
-	db 64
-	xor eax, -120
-	db 64
-	xor eax, 24
-	lea eax, [rax+rax*8+9]
-	db 64
-	add eax, -31
-	db 64
-	xor eax, -16
-	db 64
-	add eax, 68
-	lea eax, [rax+rax*8-110]
-	db 64
-	xor eax, 64
-	db 64
-	xor eax, -40
-	db 64
-	xor eax, -8
-	db 64
-	add eax, -10
-	db 64
-	xor eax, -32
-	db 64
-	add eax, 14
-	lea eax, [rax+rax*8-46]
-	db 64
-	xor eax, -104
-	lea eax, [rax+rax*8+36]
-	db 64
-	add eax, 100
-	lea eax, [rax+rax*8-65]
-	lea eax, [rax+rax*8+27]
-	lea eax, [rax+rax*8+91]
-	db 64
-	add eax, -101
-	db 64
-	add eax, -94
-	lea eax, [rax+rax*8-10]
-	db 64
-	xor eax, 80
-	db 64
-	add eax, -108
-	db 64
-	add eax, -58
-	db 64
-	xor eax, 48
-	lea eax, [rax+rax*8+73]
-	db 64
-	xor eax, -48
-	db 64
-	xor eax, 32
-	db 64
-	xor eax, -96
-	db 64
-	add eax, 118
-	db 64
-	add eax, 91
-	lea eax, [rax+rax*8+18]
-	db 64
-	add eax, -11
-	lea eax, [rax+rax*8+63]
-	db 64
-	add eax, 114
-	lea eax, [rax+rax*8+45]
-	db 64
-	add eax, -67
-	db 64
-	add eax, 53
-	lea eax, [rax+rax*8-101]
-	lea eax, [rax+rax*8-1]
-	db 64
-	xor eax, 16
-	lea eax, [rax+rax*8-37]
-	lea eax, [rax+rax*8-28]
-	lea eax, [rax+rax*8-55]
-	db 64
-	xor eax, -88
-	db 64
-	xor eax, -72
-	db 64
-	add eax, 36
-	db 64
-	xor eax, -56
-	db 64
-	add eax, 116
-	db 64
-	xor eax, 88
-	db 64
-	xor eax, -128
-	db 64
-	add eax, 50
-	db 64
-	add eax, 105
-	db 64
-	add eax, -37
-	db 64
-	xor eax, 112
-	db 64
-	xor eax, 8
-	db 64
-	xor eax, -24
-	lea eax, [rax+rax*8+118]
-	db 64
-	xor eax, 72
-	db 64
-	xor eax, -64
-	db 64
-	add eax, 40
-	lea eax, [rax+rax*8-74]
-	lea eax, [rax+rax*8+82]
-	lea eax, [rax+rax*8+54]
-	db 64
-	xor eax, 56
-	db 64
-	xor eax, 40
-	db 64
-	add eax, 87