feat: improve batch copy performance (vyperlang#3483)

per cancun, eip-5656, this commit adds the use of mcopy for memory copies. it also - adds heuristics to use loops vs unrolled loops for batch copies. - adds helper functions `vyper.codegen.core._opt_[gas,codesize,none]()` to detect optimization mode during codegen - adds `--optimize none` to CLI options, with the intent of phasing out `--no-optimize` if the ergonomics are better.
tserg · Jul 15, 2023 · 5dc3ac7 · 5dc3ac7
1 parent 593c9b8
commit 5dc3ac7
Show file tree

Hide file tree

Showing 13 changed files with 221 additions and 99 deletions.
diff --git a/.github/workflows/era-tester.yml b/.github/workflows/era-tester.yml
@@ -101,11 +101,11 @@ jobs:
       if: ${{ github.ref != 'refs/heads/master' }}
       run: |
         cd era-compiler-tester
-        cargo run --release --bin compiler-tester -- -v --path=tests/vyper/ --mode="M0B0 ${{ env.VYPER_VERSION }}"
+        cargo run --release --bin compiler-tester -- --path=tests/vyper/ --mode="M0B0 ${{ env.VYPER_VERSION }}"
 
     - name: Run tester (slow)
       # Run era tester across the LLVM optimization matrix
       if: ${{ github.ref == 'refs/heads/master' }}
       run: |
         cd era-compiler-tester
-        cargo run --release --bin compiler-tester -- -v --path=tests/vyper/ --mode="M*B* ${{ env.VYPER_VERSION }}"
+        cargo run --release --bin compiler-tester -- --path=tests/vyper/ --mode="M*B* ${{ env.VYPER_VERSION }}"
diff --git a/setup.cfg b/setup.cfg
@@ -31,7 +31,6 @@ addopts = -n auto
 	--cov-report html
 	--cov-report xml
 	--cov=vyper
-	--hypothesis-show-statistics
 python_files = test_*.py
 testpaths = tests
 markers =

diff --git a/tests/compiler/test_opcodes.py b/tests/compiler/test_opcodes.py
@@ -59,5 +59,8 @@ def test_get_opcodes(evm_version):
         assert "PUSH0" in ops
 
     if evm_version in ("cancun",):
-        assert "TLOAD" in ops
-        assert "TSTORE" in ops
+        for op in ("TLOAD", "TSTORE", "MCOPY"):
+            assert op in ops
+    else:
+        for op in ("TLOAD", "TSTORE", "MCOPY"):
+            assert op not in ops
diff --git a/tests/parser/functions/test_slice.py b/tests/parser/functions/test_slice.py
@@ -1,4 +1,6 @@
+import hypothesis.strategies as st
 import pytest
+from hypothesis import given, settings
 
 from vyper.exceptions import ArgumentException
 
@@ -9,14 +11,6 @@ def _generate_bytes(length):
     return bytes(list(range(length)))
 
 
-# good numbers to try
-_fun_numbers = [0, 1, 5, 31, 32, 33, 64, 99, 100, 101]
-
-
-# [b"", b"\x01", b"\x02"...]
-_bytes_examples = [_generate_bytes(i) for i in _fun_numbers if i <= 100]
-
-
 def test_basic_slice(get_contract_with_gas_estimation):
     code = """
 @external
@@ -31,12 +25,16 @@ def slice_tower_test(inp1: Bytes[50]) -> Bytes[50]:
     assert x == b"klmnopqrst", x
 
 
-@pytest.mark.parametrize("bytesdata", _bytes_examples)
-@pytest.mark.parametrize("start", _fun_numbers)
+# note: optimization boundaries at 32, 64 and 320 depending on mode
+_draw_1024 = st.integers(min_value=0, max_value=1024)
+_draw_1024_1 = st.integers(min_value=1, max_value=1024)
+_bytes_1024 = st.binary(min_size=0, max_size=1024)
+
+
 @pytest.mark.parametrize("literal_start", (True, False))
-@pytest.mark.parametrize("length", _fun_numbers)
 @pytest.mark.parametrize("literal_length", (True, False))
-@pytest.mark.fuzzing
+@given(start=_draw_1024, length=_draw_1024, length_bound=_draw_1024_1, bytesdata=_bytes_1024)
+@settings(max_examples=25, deadline=None)
 def test_slice_immutable(
     get_contract,
     assert_compile_failed,
@@ -46,47 +44,48 @@ def test_slice_immutable(
     literal_start,
     length,
     literal_length,
+    length_bound,
 ):
     _start = start if literal_start else "start"
     _length = length if literal_length else "length"
 
     code = f"""
-IMMUTABLE_BYTES: immutable(Bytes[100])
-IMMUTABLE_SLICE: immutable(Bytes[100])
+IMMUTABLE_BYTES: immutable(Bytes[{length_bound}])
+IMMUTABLE_SLICE: immutable(Bytes[{length_bound}])
 
 @external
-def __init__(inp: Bytes[100], start: uint256, length: uint256):
+def __init__(inp: Bytes[{length_bound}], start: uint256, length: uint256):
     IMMUTABLE_BYTES = inp
     IMMUTABLE_SLICE = slice(IMMUTABLE_BYTES, {_start}, {_length})
 
 @external
-def do_splice() -> Bytes[100]:
+def do_splice() -> Bytes[{length_bound}]:
     return IMMUTABLE_SLICE
     """
 
+    def _get_contract():
+        return get_contract(code, bytesdata, start, length)
+
     if (
-        (start + length > 100 and literal_start and literal_length)
-        or (literal_length and length > 100)
-        or (literal_start and start > 100)
+        (start + length > length_bound and literal_start and literal_length)
+        or (literal_length and length > length_bound)
+        or (literal_start and start > length_bound)
         or (literal_length and length < 1)
     ):
-        assert_compile_failed(
-            lambda: get_contract(code, bytesdata, start, length), ArgumentException
-        )
-    elif start + length > len(bytesdata):
-        assert_tx_failed(lambda: get_contract(code, bytesdata, start, length))
+        assert_compile_failed(lambda: _get_contract(), ArgumentException)
+    elif start + length > len(bytesdata) or (len(bytesdata) > length_bound):
+        # deploy fail
+        assert_tx_failed(lambda: _get_contract())
     else:
-        c = get_contract(code, bytesdata, start, length)
+        c = _get_contract()
         assert c.do_splice() == bytesdata[start : start + length]
 
 
 @pytest.mark.parametrize("location", ("storage", "calldata", "memory", "literal", "code"))
-@pytest.mark.parametrize("bytesdata", _bytes_examples)
-@pytest.mark.parametrize("start", _fun_numbers)
 @pytest.mark.parametrize("literal_start", (True, False))
-@pytest.mark.parametrize("length", _fun_numbers)
 @pytest.mark.parametrize("literal_length", (True, False))
-@pytest.mark.fuzzing
+@given(start=_draw_1024, length=_draw_1024, length_bound=_draw_1024_1, bytesdata=_bytes_1024)
+@settings(max_examples=25, deadline=None)
 def test_slice_bytes(
     get_contract,
     assert_compile_failed,
@@ -97,9 +96,10 @@ def test_slice_bytes(
     literal_start,
     length,
     literal_length,
+    length_bound,
 ):
     if location == "memory":
-        spliced_code = "foo: Bytes[100] = inp"
+        spliced_code = f"foo: Bytes[{length_bound}] = inp"
         foo = "foo"
     elif location == "storage":
         spliced_code = "self.foo = inp"
@@ -120,31 +120,38 @@ def test_slice_bytes(
     _length = length if literal_length else "length"
 
     code = f"""
-foo: Bytes[100]
-IMMUTABLE_BYTES: immutable(Bytes[100])
+foo: Bytes[{length_bound}]
+IMMUTABLE_BYTES: immutable(Bytes[{length_bound}])
 @external
-def __init__(foo: Bytes[100]):
+def __init__(foo: Bytes[{length_bound}]):
     IMMUTABLE_BYTES = foo
 
 @external
-def do_slice(inp: Bytes[100], start: uint256, length: uint256) -> Bytes[100]:
+def do_slice(inp: Bytes[{length_bound}], start: uint256, length: uint256) -> Bytes[{length_bound}]:
     {spliced_code}
     return slice({foo}, {_start}, {_length})
     """
 
-    length_bound = len(bytesdata) if location == "literal" else 100
+    def _get_contract():
+        return get_contract(code, bytesdata)
+
+    data_length = len(bytesdata) if location == "literal" else length_bound
     if (
-        (start + length > length_bound and literal_start and literal_length)
-        or (literal_length and length > length_bound)
-        or (literal_start and start > length_bound)
+        (start + length > data_length and literal_start and literal_length)
+        or (literal_length and length > data_length)
+        or (location == "literal" and len(bytesdata) > length_bound)
+        or (literal_start and start > data_length)
         or (literal_length and length < 1)
     ):
-        assert_compile_failed(lambda: get_contract(code, bytesdata), ArgumentException)
+        assert_compile_failed(lambda: _get_contract(), ArgumentException)
+    elif len(bytesdata) > data_length:
+        # deploy fail
+        assert_tx_failed(lambda: _get_contract())
     elif start + length > len(bytesdata):
-        c = get_contract(code, bytesdata)
+        c = _get_contract()
         assert_tx_failed(lambda: c.do_slice(bytesdata, start, length))
     else:
-        c = get_contract(code, bytesdata)
+        c = _get_contract()
         assert c.do_slice(bytesdata, start, length) == bytesdata[start : start + length], code
 
 

diff --git a/tests/parser/types/test_dynamic_array.py b/tests/parser/types/test_dynamic_array.py
@@ -2,7 +2,6 @@
 
 import pytest
 
-from vyper.compiler.settings import OptimizationLevel
 from vyper.exceptions import (
     ArgumentException,
     ArrayIndexException,
@@ -1585,14 +1584,9 @@ def bar2() -> uint256:
         newFoo.b1[1][0][0].a1[0][1][1] + \\
         newFoo.b1[0][1][0].a1[0][0][0]
     """
-
-    if optimize == OptimizationLevel.NONE:
-        # fails at assembly stage with too many stack variables
-        assert_compile_failed(lambda: get_contract(code), Exception)
-    else:
-        c = get_contract(code)
-        assert c.bar() == [[[3, 7], [7, 3]], [[7, 3], [0, 0]]]
-        assert c.bar2() == 0
+    c = get_contract(code)
+    assert c.bar() == [[[3, 7], [7, 3]], [[7, 3], [0, 0]]]
+    assert c.bar2() == 0
 
 
 def test_tuple_of_lists(get_contract):

diff --git a/vyper/cli/vyper_compile.py b/vyper/cli/vyper_compile.py
@@ -105,7 +105,7 @@ def _parse_args(argv):
         dest="evm_version",
     )
     parser.add_argument("--no-optimize", help="Do not optimize", action="store_true")
-    parser.add_argument("--optimize", help="Optimization flag", choices=["gas", "codesize"])
+    parser.add_argument("--optimize", help="Optimization flag", choices=["gas", "codesize", "none"])
     parser.add_argument(
         "--no-bytecode-metadata", help="Do not add metadata to bytecode", action="store_true"
     )