ab124776a0
Code blocks now have a varying level of granularity in the page and dirty masks. Most blocks have 64-byte granularity, but blocks that are repeatedly modified drop to 1-byte granularity. This reduces the maximum size of the affected block significantly, but reduces recompilation due to data located too close to code. If the block is still marked as dirty, then it is recompiled without any immediate instruction parameters being baked into the recompiled code, instead being fetched from the RAM array as needed. This severely reduces recompilation rates on some SMC-heavy games, eg Duke Nukem 3D, System Shock, Screamer etc, giving a major speedup.
57 lines
3.7 KiB
C
57 lines
3.7 KiB
C
#include "ibm.h"
|
|
|
|
#include "x86.h"
|
|
#include "x86_flags.h"
|
|
#include "386_common.h"
|
|
#include "codegen.h"
|
|
#include "codegen_accumulate.h"
|
|
#include "codegen_ir.h"
|
|
#include "codegen_ops.h"
|
|
#include "codegen_ops_mmx_arith.h"
|
|
#include "codegen_ops_helpers.h"
|
|
|
|
#define ropParith(func) \
|
|
uint32_t rop ## func(codeblock_t *block, ir_data_t *ir, uint8_t opcode, uint32_t fetchdat, uint32_t op_32, uint32_t op_pc) \
|
|
{ \
|
|
int dest_reg = (fetchdat >> 3) & 7; \
|
|
\
|
|
uop_MMX_ENTER(ir); \
|
|
codegen_mark_code_present(block, cs+op_pc, 1); \
|
|
if ((fetchdat & 0xc0) == 0xc0) \
|
|
{ \
|
|
int src_reg = fetchdat & 7; \
|
|
uop_ ## func(ir, IREG_MM(dest_reg), IREG_MM(dest_reg), IREG_MM(src_reg)); \
|
|
} \
|
|
else \
|
|
{ \
|
|
x86seg *target_seg; \
|
|
\
|
|
uop_MOV_IMM(ir, IREG_oldpc, cpu_state.oldpc); \
|
|
target_seg = codegen_generate_ea(ir, op_ea_seg, fetchdat, op_ssegs, &op_pc, op_32, 0); \
|
|
codegen_check_seg_read(block, ir, target_seg); \
|
|
uop_MEM_LOAD_REG(ir, IREG_temp0_Q, ireg_seg_base(target_seg), IREG_eaaddr); \
|
|
uop_ ## func(ir, IREG_MM(dest_reg), IREG_MM(dest_reg), IREG_temp0_Q); \
|
|
} \
|
|
\
|
|
return op_pc + 1; \
|
|
}
|
|
|
|
ropParith(PADDB)
|
|
ropParith(PADDW)
|
|
ropParith(PADDD)
|
|
ropParith(PADDSB)
|
|
ropParith(PADDSW)
|
|
ropParith(PADDUSB)
|
|
ropParith(PADDUSW)
|
|
|
|
ropParith(PSUBB)
|
|
ropParith(PSUBW)
|
|
ropParith(PSUBD)
|
|
ropParith(PSUBSB)
|
|
ropParith(PSUBSW)
|
|
ropParith(PSUBUSB)
|
|
ropParith(PSUBUSW)
|
|
|
|
ropParith(PMADDWD)
|
|
ropParith(PMULHW)
|
|
ropParith(PMULLW)
|