cpython/Include/internal/pycore_uop.h
Mark Shannon 469f191a85
GH-135379: Top of stack caching for the JIT. (GH-135465)
Uses three registers to cache values at the top of the evaluation stack
This significantly reduces memory traffic for smaller, more common uops.
2025-12-11 10:32:52 +00:00

58 lines
1.3 KiB
C

#ifndef Py_CORE_UOP_H
#define Py_CORE_UOP_H
#ifdef __cplusplus
extern "C" {
#endif
#ifndef Py_BUILD_CORE
# error "this header requires Py_BUILD_CORE define"
#endif
#include <stdint.h>
/* Depending on the format,
* the 32 bits between the oparg and operand are:
* UOP_FORMAT_TARGET:
* uint32_t target;
* UOP_FORMAT_JUMP
* uint16_t jump_target;
* uint16_t error_target;
*/
typedef struct _PyUOpInstruction{
uint16_t opcode:15;
uint16_t format:1;
uint16_t oparg;
union {
uint32_t target;
struct {
uint16_t jump_target;
uint16_t error_target;
};
};
uint64_t operand0; // A cache entry
uint64_t operand1;
#ifdef Py_STATS
uint64_t execution_count;
#endif
} _PyUOpInstruction;
// This is the length of the trace we translate initially.
#ifdef Py_DEBUG
// With asserts, the stencils are a lot larger
#define UOP_MAX_TRACE_LENGTH 2000
#else
#define UOP_MAX_TRACE_LENGTH 5000
#endif
#define UOP_BUFFER_SIZE (UOP_MAX_TRACE_LENGTH * sizeof(_PyUOpInstruction))
/* Bloom filter with m = 256
* https://en.wikipedia.org/wiki/Bloom_filter */
#define _Py_BLOOM_FILTER_WORDS 8
typedef struct {
uint32_t bits[_Py_BLOOM_FILTER_WORDS];
} _PyBloomFilter;
#ifdef __cplusplus
}
#endif
#endif /* !Py_INTERNAL_UOP_H */