Research 140, 027's stage 1 measured: SHA-256 written in aup (its examples/sha256.aup) right for FIPS 180-2's examples and 138 more messages on every path, in make check against hashlib; 52 lines against Python's 28 (the bar missed: no formatting, no bytes joined or sliced, no lists as values, moved into stage 2), 176 times C's time and 0.43 of plain Python's (1,591 ns a byte; a block's 19,129 instructions, 39% of them the inlined fn's literals not folded); 044's check, time.c against the same algorithm in C (digests compared first) and the Python reference

1 files changed, 46 insertions, 0 deletions

diff --git a/research/experiments/044-specs/check.py b/research/experiments/044-specs/check.py
new file mode 100755
index 0000000..bc43090
--- /dev/null
+++ b/research/experiments/044-specs/check.py
@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+"""Research 140 / design 027 stage 1: SHA-256 written in aup (aup's examples/sha256.aup).
+
+Builds it with aup (AUP, default the sibling checkout), runs FIPS 180-2's
+examples and messages of every length 0-129 and some longer ones on Pure's
+three paths (batches, rounds, all compiled) and the default, each digest
+against hashlib; then counts lines (code lines: neither blank nor a comment;
+brace lines: a closing brace alone) of sha256.aup and of sha256.py's
+algorithm (above its main). One JSON line."""
+import hashlib, json, os, random, subprocess, sys, tempfile
+
+here = os.path.dirname(os.path.abspath(__file__))
+pure = os.path.normpath(os.path.join(here, '../../..'))
+aup = os.environ.get('AUP', os.path.join(pure, '..', 'aup'))
+
+def lines(path, stop=None):
+    code = braces = 0
+    for line in open(path):
+        if stop and line.startswith(stop): break
+        text = line.strip()
+        if not text or text.startswith('#'): continue
+        code += 1
+        braces += text == '}'
+    return code, braces
+
+random.seed(140)
+messages = [b'', b'abc', b'abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq',
+            b'abcdefghbcdefghicdefghijdefghijkefghijklfghijklmghijklmnhijklmnoijklmnopjklmnopqklmnopqrlmnopqrsmnopqrstnopqrstu']
+messages += [bytes(random.randrange(256) for _ in range(n)) for n in list(range(130)) + [255, 256, 511, 512, 1000, 4096, 10000, 32000]]
+with tempfile.TemporaryDirectory() as tmp:
+    module = os.path.join(tmp, 'sha256.pmod')
+    subprocess.run([os.path.join(aup, 'build', 'aup'), 'build', os.path.join(aup, 'examples', 'sha256.aup'), '-o', module], check=True)
+    given = ''.join(f"message hash {m.hex() or '-'}\n" for m in messages).encode()
+    paths = {}
+    for name, env in (('batches', {'PURE_JIT': '0'}), ('rounds', {'PURE_JIT': '0', 'PURE_BATCH': '0'}),
+                      ('all', {'PURE_JIT': 'all'}), ('default', {})):
+        out = subprocess.run([os.path.join(pure, 'build', 'pure-run'), module], input=given, capture_output=True,
+                             env=dict(os.environ, **env), check=True).stdout.decode().splitlines()
+        paths[name] = sum(json.loads(o)['states']['digest'] == hashlib.sha256(m).hexdigest() and json.loads(o)['fault'] == 'none'
+                          for m, o in zip(messages, out)) if len(out) == len(messages) else 0
+aup_code, aup_braces = lines(os.path.join(aup, 'examples', 'sha256.aup'))
+python_code, _ = lines(os.path.join(here, 'sha256.py'), stop='if __name__')
+ok = all(n == len(messages) for n in paths.values())
+print(json.dumps({'messages': len(messages), 'right': paths, 'aup_lines': aup_code, 'aup_brace_lines': aup_braces,
+                  'python_lines': python_code}))
+sys.exit(0 if ok else 1)