ARM: default to NUDUPL squaring, drop phased pipeline, and add NUDUPL profiling + CI reliability fixes

.github/workflows/rust.yml

@@ -20,21 +20,43 @@ permissions:
 
 jobs:
   fuzz_targets:
-    name: Run fuzzers
+    name: Run fuzzers (${{ matrix.target }})
     runs-on: ubuntu-latest
     env:
       CARGO_PROFILE_RELEASE_LTO: false
+    strategy:
+      fail-fast: false
+      matrix:
+        target:
+          - create_discriminant
+          - prove
+          - verify
+          - verify_n_wesolowski
     steps:
       - uses: actions/checkout@v6
       - uses: dtolnay/rust-toolchain@nightly
 
+      - name: Cache cargo registry + build artifacts
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cargo/bin
+            ~/.cargo/registry
+            ~/.cargo/git
+            target
+            rust_bindings/fuzz/corpus
+          key: ${{ runner.os }}-rust-fuzz-${{ hashFiles('Cargo.lock') }}
+
       - name: Install cargo-fuzz
-        run: cargo +nightly install cargo-fuzz
+        run: |
+          if ! command -v cargo-fuzz >/dev/null 2>&1; then
+            cargo +nightly install cargo-fuzz --locked
+          fi
 
-      - name: Cargo fuzz
+      - name: Cargo fuzz (${{ matrix.target }})
         run: |
           cd rust_bindings
-          cargo fuzz list | xargs -I "%" sh -c "cargo +nightly fuzz run % -- -max_total_time=600 || exit 255"
+          cargo +nightly fuzz run ${{ matrix.target }} -- -max_total_time=600
 
   lint:
     name: Lint
@@ -110,7 +132,10 @@ jobs:
 
       - name: Install libclang-dev on Linux
         if: matrix.os.name == 'Ubuntu'
-        run: sudo apt-get install libclang-dev -y
+        run: |
+          # Avoid transient 404s from stale apt indices / mirror lag.
+          sudo apt-get update -y -o Acquire::Retries=3
+          sudo apt-get install libclang-dev -y
 
       - name: Set up Rust
         uses: dtolnay/rust-toolchain@stable

.github/workflows/test.yaml

@@ -17,7 +17,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-13-intel, ubuntu-latest]
+        os: [macos-13-intel, macos-13-arm64, ubuntu-latest]
         config: [optimized=1, TSAN=1, ASAN=1]
 
     steps:
@@ -34,6 +34,8 @@ jobs:
     - name: Build vdf-client on Ubuntu
       if: startsWith(matrix.os, 'ubuntu')
       run: |
+        # Avoid transient 404s from stale apt indices / mirror lag.
+        sudo apt-get update -y -o Acquire::Retries=3
         sudo apt-get install libgmp-dev libboost-python-dev libpython3-dev libboost-system-dev build-essential -y
         cd src
         make ${{ matrix.config }} -f Makefile.vdf-client
@@ -54,7 +56,11 @@ jobs:
         echo "Running 2weso_test"
         ./2weso_test
         echo "Running prover_test"
-        ./prover_test
+        if [[ "${{ matrix.os }}" == ubuntu* ]]; then
+          ./prover_test
+        else
+          CHIAVDF_PROVER_TEST_FAST=1 ./prover_test
+        fi
 
     - name: Test vdf-client
       if: matrix.config != 'optimized=1'
@@ -73,7 +79,11 @@ jobs:
       run: |
         cd src
         echo "Running prover_test"
-        ./prover_test
+        if [[ "${{ matrix.os }}" == ubuntu* ]]; then
+          ./prover_test
+        else
+          CHIAVDF_PROVER_TEST_FAST=1 ./prover_test
+        fi
 
     - name: Benchmark vdf-client
       if: matrix.config == 'optimized=1'

README.md

@@ -36,7 +36,8 @@ MacOS and Linux, chiavdf can be used to compile vdf_client and vdf_bench.
 vdf_client is the core VDF process that completes the Proof of Time submitted
 to it by the Timelord. The repo also includes a benchmarking tool to get a
 sense of the iterations per second of a given CPU called vdf_bench. Try
-`./vdf_bench square_asm 250000` for an ips estimate.
+`./vdf_bench square_asm 250000` for an ips estimate on x86/x64 (phased/asm
+pipeline). On non-x86 architectures, use `./vdf_bench square 250000` (NUDUPL).
 
 To build vdf_client set the environment variable BUILD_VDF_CLIENT to "Y".
 `export BUILD_VDF_CLIENT=Y`.
@@ -60,6 +61,9 @@ If you're running a timelord, the following tests are available, depending of wh
 
 Those tests will simulate the vdf_client and verify for correctness the produced proofs.
 
+Note: `./prover_test` defaults to a long soak/stress run. Set
+`CHIAVDF_PROVER_TEST_FAST=1` to run a short, CI-friendly correctness check.
+
 ## Contributing and workflow
 
 Contributions are welcome and more details are available in chia-blockchain's

pyproject.toml

@@ -32,7 +32,10 @@ before-build = "python -m pip install --upgrade pip"
 
 [tool.cibuildwheel.macos]
 build-verbosity = 0
-before-all = "brew install gmp boost cmake"
+before-all = """
+brew --prefix gmp >/dev/null 2>&1 || brew install gmp
+brew install boost cmake
+"""
 before-build = "python -m pip install --upgrade pip"
 environment = {MACOSX_DEPLOYMENT_TARGET="13", SYSTEM_VERSION_COMPAT=0, BUILD_VDF_CLIENT="N"}
 

setup.py

@@ -3,6 +3,7 @@
 import shutil
 import subprocess
 import sys
+from pathlib import Path
 
 from setuptools import Command, Extension, setup
 from setuptools.command.build import build
@@ -134,14 +135,19 @@ def build_extension(self, ext):
 build.sub_commands.append(("build_hook", lambda x: True))  # type: ignore
 install.sub_commands.append(("install_hook", lambda x: True))
 
+# Wheel metadata generation on Windows can run with a non-UTF8 default encoding.
+# Read `README.md` explicitly as UTF-8 so `long_description` is robust across runners.
+_readme_path = Path(__file__).resolve().parent / "README.md"
+_long_description = _readme_path.read_text(encoding="utf-8")
+
 setup(
     name="chiavdf",
     author="Florin Chirica",
     author_email="florin@chia.net",
     description="Chia vdf verification (wraps C++)",
     license="Apache-2.0",
     python_requires=">=3.9",
-    long_description=open("README.md").read(),
+    long_description=_long_description,
     long_description_content_type="text/markdown",
     url="https://github.com/Chia-Network/chiavdf",
     ext_modules=[CMakeExtension("chiavdf", "src")],

src/Makefile.vdf-client

@@ -1,16 +1,32 @@
 UNAME := $(shell uname)
+ARCH := $(shell uname -m)
 
 ifneq (,$(findstring clang, $(shell $(CXX) --version)))
 NOPIE = -fno-PIE
 else
 NOPIE = -no-pie
 endif
+# macOS arm64 ignores -no_pie and warns; omit to avoid deprecation warnings
+ifeq ($(UNAME),Darwin)
+ifneq ($(filter $(ARCH),arm64),)
+NOPIE =
+endif
+endif
 
 LDFLAGS += -flto $(NOPIE) -g
 LDLIBS += -lgmpxx -lgmp -pthread
 CXXFLAGS += -flto -std=c++1z -D VDF_MODE=0 -D FAST_MACHINE=1 -pthread $(NOPIE) -fvisibility=hidden
 ifeq ($(UNAME),Darwin)
 CXXFLAGS += -D CHIAOSX=1
+# Homebrew (common on macOS) installs boost/gmp to /opt/homebrew or /usr/local
+ifneq ($(wildcard /opt/homebrew/include/boost/asio.hpp),)
+CXXFLAGS += -I/opt/homebrew/include
+LDFLAGS += -L/opt/homebrew/lib
+endif
+ifneq ($(wildcard /usr/local/include/boost/asio.hpp),)
+CXXFLAGS += -I/usr/local/include
+LDFLAGS += -L/usr/local/lib
+endif
 endif
 
 OPT_CFLAGS = -O3 -g
@@ -27,13 +43,20 @@ endif
 
 .PHONY: all clean
 
+# aarch64 (Linux), arm64 (macOS Apple Silicon): no x86 asm objects
+ifneq ($(filter $(ARCH),aarch64 arm64),)
+ASM_OBJS =
+else
+ASM_OBJS = asm_compiled.o avx2_asm_compiled.o avx512_asm_compiled.o
+endif
+
 BINS = vdf_client prover_test 1weso_test 2weso_test vdf_bench
 all: $(BINS)
 
 clean:
 	rm -f *.o hw/*.o $(BINS) compile_asm emu_hw_test hw_test hw_vdf_client emu_hw_vdf_client
 
-$(BINS) avx512_test: %: %.o lzcnt.o asm_compiled.o avx2_asm_compiled.o avx512_asm_compiled.o
+$(BINS) avx512_test: %: %.o lzcnt.o $(ASM_OBJS)
 	$(CXX) $(LDFLAGS) -o $@ $^ $(LDLIBS)
 
 $(addsuffix .o,$(BINS)) avx512_test.o: CXXFLAGS += $(OPT_CFLAGS)

src/avx512_integer.h

@@ -123,6 +123,7 @@ void mpz_impl_set_mul(
     const mpz<expected_size_a, padded_size_a>& a,
     const mpz<expected_size_b, padded_size_b>& b
 ) {
+#if defined(ARCH_X86) || defined(ARCH_X64)
     if (enable_avx512_ifma) {
         typename avx512_integer_for_size<expected_size_a>::i a_avx512;
         typename avx512_integer_for_size<expected_size_b>::i b_avx512;
@@ -132,7 +133,9 @@ void mpz_impl_set_mul(
         b_avx512=b;
         out_avx512.set_mul(a_avx512, b_avx512);
         out_avx512.assign(out);
-    } else {
+    } else
+#endif
+    {
         mpz_mul(out._(), a._(), b._());
     }
 }

src/callback.h

@@ -2,6 +2,7 @@
 #define CALLBACK_H
 
 #include "util.h"
+#include "nudupl_listener.h"
 
 // Applies to n-weso.
 const int kWindowSize = 20;
@@ -32,13 +33,19 @@ class WesolowskiCallback :public INUDUPLListener {
         switch(type) {
             case NL_SQUARESTATE:
             {
+#if defined(ARCH_X86) || defined(ARCH_X64)
                 //cout << "NL_SQUARESTATE" << endl;
                 uint64 res;
 
                 square_state_type *square_state=(square_state_type *)data;
 
                 if(!square_state->assign(mulf->a, mulf->b, mulf->c, res))
                     cout << "square_state->assign failed" << endl;
+#else
+                // Phased pipeline is x86/x64-only.
+                (void)data;
+                cout << "NL_SQUARESTATE unsupported on this architecture" << endl;
+#endif
                 break;
             }
             case NL_FORM:

src/chiavdf_profile.h

@@ -0,0 +1,40 @@
+#ifndef CHIAVDF_PROFILE_H
+#define CHIAVDF_PROFILE_H
+
+#include <cstdint>
+
+// This header centralizes optional profiling hooks used by `vdf.h` (driver) and
+// hot-loop primitives like NUDUPL (`nucomp.h`). Everything is no-op unless:
+// - `VDF_TEST` is enabled (VDF_MODE=1), and
+// - the caller sets `chiavdf_nudupl_profile_sink` (and optionally enables timing).
+
+struct chiavdf_nudupl_profile_stats {
+    // Outer-loop counts (from `repeated_square_nudupl`).
+    uint64_t iters = 0;
+    uint64_t reduce_calls = 0;
+    uint64_t reduce_skipped = 0;
+    uint64_t max_a_limbs = 0;
+
+    // Outer-loop timing (from `repeated_square_nudupl`).
+    uint64_t nudupl_form_time_ns = 0;
+    uint64_t reduce_time_ns = 0;
+
+    // Inner-loop breakdown (from `qfb_nudupl`).
+    uint64_t qfb_nudupl_calls = 0;
+    uint64_t b_negative = 0;
+    uint64_t branch_a_lt_L = 0;
+    uint64_t branch_a_ge_L = 0;
+
+    uint64_t gcdext_time_ns = 0;
+    uint64_t gcdext_s_eq_1 = 0;
+    uint64_t gcdext_s_ne_1 = 0;
+    uint64_t xgcd_partial_time_ns = 0;
+    uint64_t else_branch_time_ns = 0; // time spent in the a>=L branch overall
+};
+
+#if defined(VDF_TEST)
+inline thread_local chiavdf_nudupl_profile_stats* chiavdf_nudupl_profile_sink = nullptr;
+inline thread_local bool chiavdf_nudupl_profile_timing_enabled = false;
+#endif
+
+#endif // CHIAVDF_PROFILE_H