René's URL Explorer Experiment

Title: gh-146306: Optimize float operations by mutating uniquely-referenced operands in place (JIT only) by eendebakpt · Pull Request #146307 · python/cpython · GitHub

Open Graph Title: gh-146306: Optimize float operations by mutating uniquely-referenced operands in place (JIT only) by eendebakpt · Pull Request #146307 · python/cpython

X Title: gh-146306: Optimize float operations by mutating uniquely-referenced operands in place (JIT only) by eendebakpt · Pull Request #146307 · python/cpython

Description: We can add the following tier 2 micro-ops that mutate the uniquely-referenced operand: _BINARY_OP_ADD_FLOAT_INPLACE / _INPLACE_RIGHT — unique LHS / RHS _BINARY_OP_SUBTRACT_FLOAT_INPLACE / _INPLACE_RIGHT — unique LHS / RHS _BINARY_OP_MULTIPLY_FLOAT_INPLACE / _INPLACE_RIGHT — unique LHS / RHS _UNARY_NEGATIVE_FLOAT_INPLACE — unique operand The _RIGHT variants handle commutative ops (add, multiply) plus subtract when only the RHS is unique. The optimizer emits these in optimizer_bytecodes.c when PyJitRef_IsUnique(left) or PyJitRef_IsUnique(right) is true and the operand is a known float. The mutated operand is marked as borrowed so the following _POP_TOP becomes _POP_TOP_NOP. Micro-benchmarks: Expression main optimized Speedup total += a*b + c 24.0 ns/iter 11.5 ns/iter 2.1x total += a + b 16.9 ns/iter 11.0 ns/iter 1.5x total += a*b + c*d 28.5 ns/iter 18.3 ns/iter 1.6x pyperformance nbody (20k iterations): main optimized Speedup nbody 60.6 ms 49.0 ms 1.19x (19% faster) Followup Some operations that could be added in followup PR's: division of floats (same as this PR, but needs to handle division by zero), operations on a float and an (compact) int with a uniquely referenced float, integer operations (but this is more involved because of small ints and number of digits), operations with complex numbers (same as this PR, but maybe the use case for complex is less). Script """Demo script for the inplace float mutation optimization in the tier 2 optimizer. ./configure --enable-experimental-jit=interpreter --with-pydebug ./configure --enable-experimental-jit=yes --with-pydebug Usage: ./python jit_float_demo.py # filtered trace (float-related ops) ./python jit_float_demo.py --all # full trace (all ops) """ import sys import timeit SHOW_ALL = "--all" in sys.argv # --- System info --- print("=" * 60) print("CPython JIT / Tier 2 Demo") print("=" * 60) print(f"Python version: {sys.version}") print(f"Debug build: {hasattr(sys, 'gettotalrefcount')}") print(f"Free-threaded: {not sys._is_gil_enabled()}") jit_mod = getattr(sys, "_jit", None) if jit_mod is not None: print(f"JIT available: {jit_mod.is_available()}") print(f"JIT enabled: {jit_mod.is_enabled()}") else: print("JIT: not compiled in") tier2 = False try: from _testinternalcapi import TIER2_THRESHOLD tier2 = True print(f"Tier 2: enabled (threshold={TIER2_THRESHOLD})") except (ImportError, AttributeError): print("Tier 2: disabled (build without _Py_TIER2)") print() # --- Example functions --- def f_adds(n, a, b, c): """a*b + c per iteration — the multiply result is unique and reused.""" total = 0.0 for i in range(n): total = a + b + c return total def f_chain(n, a, b, c): """a*b + c per iteration — the multiply result is unique and reused.""" total = 0.0 for i in range(n): total += a * b + c return total def f_simple_add(n, a, b): """a + b per iteration — no unique intermediate.""" total = 0.0 for i in range(n): total += a + b return total def f_long_chain(n, a, b, c, d): """a*b + c*d per iteration — two unique intermediates.""" total = 0.0 for i in range(n): total += a * b + c * d return total def f_negate(n, a, b): """a*b + c*d per iteration — two unique intermediates.""" total = 0.0 for i in range(n): total = - (a + b) return total # --- Warm up to trigger tier 2 --- LOOP = 10_000 f_adds(LOOP, 2.0, 3.0, 4.0) f_chain(LOOP, 2.0, 3.0, 4.0) f_simple_add(LOOP, 2.0, 3.0) f_long_chain(LOOP, 2.0, 3.0, 4.0, 5.0) # --- Op annotation --- def annotate_op(name, oparg, func): """Return a human-readable annotation for a uop.""" varnames = func.__code__.co_varnames consts = func.__code__.co_consts # _LOAD_FAST_BORROW_3 → local index 3 for prefix in ("_LOAD_FAST_BORROW_", "_LOAD_FAST_", "_SWAP_FAST_"): if name.startswith(prefix): idx = int(name[len(prefix):]) local = varnames[idx] if idx < len(varnames) else f"local{idx}" return local # _LOAD_CONST_INLINE_BORROW etc — operand is a pointer, not useful # but if oparg is a small index into consts, show it if "LOAD_CONST" in name and oparg < len(consts): return repr(consts[oparg]) # Binary ops if "MULTIPLY" in name: return "*" if "SUBTRACT" in name: return "-" if "ADD" in name and "UNICODE" not in name: return "+" # Guards if name == "_GUARD_TOS_FLOAT": return "top is float?" if name == "_GUARD_NOS_FLOAT": return "2nd is float?" if name == "_GUARD_TOS_INT": return "top is int?" if name == "_GUARD_NOS_INT": return "2nd is int?" if "NOT_EXHAUSTED" in name: return "iter not done?" # Pop / cleanup if name == "_POP_TOP_NOP": return "skip (borrowed/null)" if name == "_POP_TOP_FLOAT": return "decref float" if name == "_POP_TOP_INT": return "decref int" # Control flow if name == "_JUMP_TO_TOP": return "loop" if name == "_EXIT_TRACE": return "exit" if name == "_DEOPT": return "deoptimize" if name == "_ERROR_POP_N": return "error handler" if name == "_START_EXECUTOR": return "trace entry" if name == "_MAKE_WARM": return "warmup counter" return "" # --- Show traces --- FILTER_KEYWORDS = ( "FLOAT", "INPLACE", "BINARY_OP", "NOP", "LOAD_FAST", "LOAD_CONST", "GUARD", ) has_get_executor = False if tier2: try: from _opcode import get_executor has_get_executor = True except ImportError: pass if has_get_executor: mode = "all ops" if SHOW_ALL else "float-related ops only" print("-" * 60) print(f"Tier 2 traces ({mode})") print("-" * 60) for label, func in [ ("f_adds: total = a + b + c", f_adds), ("f_chain: total += a * b + c", f_chain), ("f_simple_add: total += a + b", f_simple_add), ("f_long_chain: total += a * b + c * d", f_long_chain), ]: code = func.__code__ found = False for i in range(len(code.co_code) // 2): try: ex = get_executor(code, i * 2) except (ValueError, TypeError, RuntimeError): continue if ex is None: continue print(f"\n {label}") for j, op in enumerate(ex): name, oparg = op[0], op[1] if not SHOW_ALL: if not any(k in name for k in FILTER_KEYWORDS): continue annotation = annotate_op(name, oparg, func) marker = " <<<" if "INPLACE" in name else "" if annotation: print(f" {j:3d}: {name:45s} # {annotation}{marker}") else: print(f" {j:3d}: {name}{marker}") found = True break if not found: print(f"\n {label}: (no executor found)") print() else: print("-" * 60) print("Tier 2 traces: skipped (tier 2 not available)") print("-" * 60) print() # --- Benchmark --- print("-" * 60) print("Benchmark") print("-" * 60) N = 2_000_000 INNER = 1000 benchmarks = [ ("total = a + b + c", lambda: f_adds(INNER, 2.0, 3.0, 4.0)), ("total += a*b + c ", lambda: f_chain(INNER, 2.0, 3.0, 4.0)), ("total += a + b ", lambda: f_simple_add(INNER, 2.0, 3.0)), ("total += a*b + c*d", lambda: f_long_chain(INNER, 2.0, 3.0, 4.0, 5.0)), ("total = - (a + b) ", lambda: f_negate(INNER, 2.0, 3.0)), ] for label, fn in benchmarks: iters = N // INNER t = timeit.timeit(fn, number=iters) ns_per = t / N * 1e9 print(f" {label}: {t:.3f}s ({ns_per:.0f} ns/iter)") print() print("The 'a*b + c' case benefits from _BINARY_OP_ADD_FLOAT_INPLACE:") print("the result of a*b is uniquely referenced, so the addition") print("mutates it in place instead of allocating a new float.") # --- N-body benchmark from pyperformance --- print() print("-" * 60) print("N-body benchmark (from pyperformance)") print("-" * 60) PI = 3.14159265358979323 SOLAR_MASS = 4 * PI * PI DAYS_PER_YEAR = 365.24 def _nbody_make_system(): bodies = [ # sun ([0.0, 0.0, 0.0], [0.0, 0.0, 0.0], SOLAR_MASS), # jupiter ([4.84143144246472090e+00, -1.16032004402742839e+00, -1.03622044471123109e-01], [1.66007664274403694e-03*DAYS_PER_YEAR, 7.69901118419740425e-03*DAYS_PER_YEAR, -6.90460016972063023e-05*DAYS_PER_YEAR], 9.54791938424326609e-04*SOLAR_MASS), # saturn ([8.34336671824457987e+00, 4.12479856412430479e+00, -4.03523417114321381e-01], [-2.76742510726862411e-03*DAYS_PER_YEAR, 4.99852801234917238e-03*DAYS_PER_YEAR, 2.30417297573763929e-05*DAYS_PER_YEAR], 2.85885980666130812e-04*SOLAR_MASS), # uranus ([1.28943695621391310e+01, -1.51111514016986312e+01, -2.23307578892655734e-01], [2.96460137564761618e-03*DAYS_PER_YEAR, 2.37847173959480950e-03*DAYS_PER_YEAR, -2.96589568540237556e-05*DAYS_PER_YEAR], 4.36624404335156298e-05*SOLAR_MASS), # neptune ([1.53796971148509165e+01, -2.59193146099879641e+01, 1.79258772950371181e-01], [2.68067772490389322e-03*DAYS_PER_YEAR, 1.62824170038242295e-03*DAYS_PER_YEAR, -9.51592254519715870e-05*DAYS_PER_YEAR], 5.15138902046611451e-05*SOLAR_MASS), ] pairs = [] for x in range(len(bodies) - 1): for y in bodies[x + 1:]: pairs.append((bodies[x], y)) return bodies, pairs def _nbody_advance(dt, n, bodies, pairs): for i in range(n): for (([x1, y1, z1], v1, m1), ([x2, y2, z2], v2, m2)) in pairs: dx = x1 - x2 dy = y1 - y2 dz = z1 - z2 mag = dt * ((dx * dx + dy * dy + dz * dz) ** (-1.5)) b1m = m1 * mag b2m = m2 * mag v1[0] -= dx * b2m v1[1] -= dy * b2m v1[2] -= dz * b2m v2[0] += dx * b1m v2[1] += dy * b1m v2[2] += dz * b1m for (r, [vx, vy, vz], m) in bodies: r[0] += dt * vx r[1] += dt * vy r[2] += dt * vz def _nbody_report_energy(bodies, pairs, e=0.0): for (((x1, y1, z1), v1, m1), ((x2, y2, z2), v2, m2)) in pairs: dx = x1 - x2 dy = y1 - y2 dz = z1 - z2 e -= (m1 * m2) / ((dx * dx + dy * dy + dz * dz) ** 0.5) for (r, [vx, vy, vz], m) in bodies: e += m * (vx * vx + vy * vy + vz * vz) / 2. return e def _nbody_offset_momentum(ref, bodies, px=0.0, py=0.0, pz=0.0): for (r, [vx, vy, vz], m) in bodies: px -= vx * m py -= vy * m pz -= vz * m (r, v, m) = ref v[0] = px / m v[1] = py / m v[2] = pz / m def bench_nbody(iterations=20000): bodies, pairs = _nbody_make_system() _nbody_offset_momentum(bodies[0], bodies) _nbody_report_energy(bodies, pairs) _nbody_advance(0.01, iterations, bodies, pairs) _nbody_report_energy(bodies, pairs) # Warmup bench_nbody(1000) NBODY_RUNS = 5 t = timeit.timeit(lambda: bench_nbody(20000), number=NBODY_RUNS) print(f" nbody (20k iterations, {NBODY_RUNS} runs): {t/NBODY_RUNS*1000:.1f} ms/run") Issue: gh-146306

Open Graph Description: We can add the following tier 2 micro-ops that mutate the uniquely-referenced operand: _BINARY_OP_ADD_FLOAT_INPLACE / _INPLACE_RIGHT — unique LHS / RHS _BINARY_OP_SUBTRACT_FLOAT_INPLACE / _INPLACE...

X Description: We can add the following tier 2 micro-ops that mutate the uniquely-referenced operand: _BINARY_OP_ADD_FLOAT_INPLACE / _INPLACE_RIGHT — unique LHS / RHS _BINARY_OP_SUBTRACT_FLOAT_INPLACE / _INPLACE...

Opengraph URL: https://github.com/python/cpython/pull/146307

X: @github

direct link

Domain: github.com

Links:

Viewport: width=device-width