research: sparse merkle tree optimizations proposed by vitalik

vitalik_merkle_optimizations/.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

vitalik_merkle_optimizations/bintrie_test.py

@@ -0,0 +1,45 @@
+import new_bintrie as t1
+import new_bintrie_optimized as t2
+import new_bintrie_hex as t3
+import time
+import binascii
+
+keys = [t1.sha3(bytes([i // 256, i % 256])) for i in range(10000)]
+
+d = t1.EphemDB()
+r = t1.new_tree(d)
+a = time.time()
+for k in keys[:1000]:
+    r = t1.update(d, r, k, k)
+print("Naive bintree time to update: %.4f" % (time.time() - a))
+print("Root: %s" % binascii.hexlify(r))
+
+d = t2.EphemDB()
+r = t2.new_tree(d)
+a = time.time()
+for k in keys[:1000]:
+    r = t2.update(d, r, k, k)
+print("DB-optimized bintree time to update: %.4f" % (time.time() - a))
+print("Root: %s" % binascii.hexlify(r))
+print("Writes: %d, reads: %d" % (d.writes, d.reads))
+d.reads = 0
+for k in keys[:500]:
+    assert t2.get(d, r, k) == k
+for k in keys[-500:]:
+    assert t2.get(d, r, k) == b'\x00' * 32
+print("Reads: %d" % d.reads)
+
+d = t3.EphemDB()
+r = t3.new_tree(d)
+a = time.time()
+for k in keys[:1000]:
+    r = t3.update(d, r, k, k)
+print("DB-optimized bintree time to update: %.4f" % (time.time() - a))
+print("Root: %s" % binascii.hexlify(r))
+print("Writes: %d, reads: %d" % (d.writes, d.reads))
+d.reads = 0
+for k in keys[:500]:
+    assert t3.get(d, r, k) == k
+for k in keys[-500:]:
+    assert t3.get(d, r, k) == b'\x00' * 32
+print("Reads: %d" % d.reads)

vitalik_merkle_optimizations/new_bintrie.py

@@ -0,0 +1,125 @@
+from ethereum.utils import sha3, encode_hex
+
+class EphemDB():
+    def __init__(self, kv=None):
+        self.kv = kv or {}
+
+    def get(self, k):
+        return self.kv.get(k, None)
+
+    def put(self, k, v):
+        self.kv[k] = v
+
+    def delete(self, k):
+        del self.kv[k]
+
+zerohashes = [b'\x00' * 32]
+for i in range(256):
+    zerohashes.insert(0, sha3(zerohashes[0] + zerohashes[0]))
+
+def new_tree(db):
+    h = b'\x00' * 32
+    for i in range(256):
+        newh = sha3(h + h)
+        db.put(newh, h + h)
+        h = newh
+    return h
+
+def key_to_path(k):
+    o = 0
+    for c in k:
+        o = (o << 8) + c
+    return o
+
+def descend(db, root, *path):
+    v = root
+    for p in path:
+        if p:
+            v = db.get(v)[32:]
+        else:
+            v = db.get(v)[:32]
+    return v
+
+def get(db, root, key):
+    v = root
+    path = key_to_path(key)
+    for i in range(256):
+        if (path >> 255) & 1:
+            v = db.get(v)[32:]
+        else:
+            v = db.get(v)[:32]
+        path <<= 1
+    return v
+
+def update(db, root, key, value):
+    v = root
+    path = path2 = key_to_path(key)
+    sidenodes = []
+    for i in range(256):
+        if (path >> 255) & 1:
+            sidenodes.append(db.get(v)[:32])
+            v = db.get(v)[32:]
+        else:
+            sidenodes.append(db.get(v)[32:])
+            v = db.get(v)[:32]
+        path <<= 1
+    v = value
+    for i in range(256):
+        if (path2 & 1):
+            newv = sha3(sidenodes[-1] + v)
+            db.put(newv, sidenodes[-1] + v)
+        else:
+            newv = sha3(v + sidenodes[-1])
+            db.put(newv, v + sidenodes[-1])
+        path2 >>= 1
+        v = newv
+        sidenodes.pop()
+    return v
+
+def make_merkle_proof(db, root, key):
+    v = root
+    path = key_to_path(key)
+    sidenodes = []
+    for i in range(256):
+        if (path >> 255) & 1:
+            sidenodes.append(db.get(v)[:32])
+            v = db.get(v)[32:]
+        else:
+            sidenodes.append(db.get(v)[32:])
+            v = db.get(v)[:32]
+        path <<= 1
+    return sidenodes
+
+def verify_proof(proof, root, key, value):
+    path = key_to_path(key)
+    v = value
+    for i in range(256):
+        if (path & 1):
+            newv = sha3(proof[-1-i] + v)
+        else:
+            newv = sha3(v + proof[-1-i])
+        path >>= 1
+        v = newv
+    return root == v
+
+def compress_proof(proof):
+    bits = bytearray(32)
+    oproof = b''
+    for i, p in enumerate(proof):
+        if p == zerohashes[i+1]:
+            bits[i // 8] ^= 1 << i % 8
+        else:
+            oproof += p
+    return bytes(bits) + oproof
+
+def decompress_proof(oproof):
+    proof = []
+    bits = bytearray(oproof[:32])
+    pos = 32
+    for i in range(256):
+        if bits[i // 8] & (1 << (i % 8)):
+            proof.append(zerohashes[i+1])
+        else:
+            proof.append(oproof[pos: pos + 32])
+            pos += 32
+    return proof