mirror of
https://github.com/python/cpython.git
synced 2026-05-16 23:40:45 +00:00
8deb8bc2e5
This makes the Tier 2 interpreter a little faster. I calculated by about 3%, though I hesitate to claim an exact number. This starts by doubling the trace size limit (to 512), making it more likely that loops fit in a trace. The rest of the approach is to only load `oparg` and `operand` in cases that use them. The code generator know when these are used. For `oparg`, it will conditionally emit ``` oparg = CURRENT_OPARG(); ``` at the top of the case block. (The `oparg` variable may be referenced multiple times by the instructions code block, so it must be in a variable.) For `operand`, it will use `CURRENT_OPERAND()` directly instead of referencing the `operand` variable, which no longer exists. (There is only one place where this will be used.)
35 lines
710 B
C
35 lines
710 B
C
#ifndef Py_INTERNAL_UOPS_H
|
|
#define Py_INTERNAL_UOPS_H
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#ifndef Py_BUILD_CORE
|
|
# error "this header requires Py_BUILD_CORE define"
|
|
#endif
|
|
|
|
#include "pycore_frame.h" // _PyInterpreterFrame
|
|
|
|
#define _Py_UOP_MAX_TRACE_LENGTH 512
|
|
|
|
typedef struct {
|
|
uint16_t opcode;
|
|
uint16_t oparg;
|
|
uint32_t target;
|
|
uint64_t operand; // A cache entry
|
|
} _PyUOpInstruction;
|
|
|
|
typedef struct {
|
|
_PyExecutorObject base;
|
|
_PyUOpInstruction trace[1];
|
|
} _PyUOpExecutorObject;
|
|
|
|
_PyInterpreterFrame *_PyUopExecute(
|
|
_PyExecutorObject *executor,
|
|
_PyInterpreterFrame *frame,
|
|
PyObject **stack_pointer);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
#endif /* !Py_INTERNAL_UOPS_H */
|