Merge branch 'master' of github.com:flexflow/flexflow-train into repo-refactor-fix-kernels-tests

Author: chenzhuofu

.flake/pkgs/ffdb/default.nix

@@ -0,0 +1,40 @@
+{ lib
+, stdenv
+, makeWrapper
+, gdb
+, python3
+, proj
+}:
+
+stdenv.mkDerivation rec {
+  pname = "ffdb";
+  version = "0.1";
+
+  pythonPath = with python3.pkgs; makePythonPath [
+    proj
+  ];
+
+  dontBuild = true;
+
+  nativeBuildInputs = [ makeWrapper ];
+
+  src = ./.;
+
+  installPhase = ''
+    mkdir -p $out/share/ffdb
+    cp ffdb.py $out/share/ffdb
+    makeWrapper ${gdb}/bin/gdb $out/bin/gdb \
+      --add-flags "-q -x $out/share/ffdb/ffdb.py" \
+      --set NIX_PYTHONPATH ${pythonPath} \
+      --prefix PATH : ${lib.makeBinPath [
+        python3
+      ]}
+    cp $out/bin/gdb $out/bin/ffdb
+  '';
+
+  nativeCheckInputs = [
+    gdb
+    python3
+    proj
+  ];
+}

.flake/pkgs/ffdb/ffdb.py

@@ -0,0 +1,7 @@
+from proj.config_file import get_config_root
+from pathlib import Path
+import gdb
+
+gdb.execute(f'directory {get_config_root(Path.cwd())}')
+gdb.prompt_hook = lambda x: '(ffdb) '
+gdb.execute('set history save on')

.github/runs-on.yml

@@ -8,4 +8,4 @@ images:
 runners:
   gpu-nvidia:
     family: ["g4dn.xlarge"]
-    image: dlami-x64
+    image: dlami-x64

.gitignore

@@ -1,3 +1,6 @@
+# gdb history
+.gdb_history
+
 # dtgen files
 *.dtg.cc
 *.dtg.h

README.md

@@ -1,8 +1,21 @@
-# FlexFlow
-![build](https://github.com/flexflow/flexflow/workflows/build/badge.svg?branch=master) ![gpu tests](https://github.com/flexflow/flexflow/workflows/gpu-ci/badge.svg?branch=master) ![multinode gpu tests](https://github.com/flexflow/flexflow/workflows/multinode-test/badge.svg?branch=master) ![docker](https://github.com/flexflow/flexflow/workflows/docker-build/badge.svg?branch=master) ![pip](https://github.com/flexflow/flexflow/workflows/pip-install/badge.svg?branch=master) ![shell-check](https://github.com/flexflow/flexflow/workflows/Shell%20Check/badge.svg?branch=master) ![clang-format](https://github.com/flexflow/flexflow/workflows/clang-format%20Check/badge.svg?branch=master) [![Documentation Status](https://readthedocs.org/projects/flexflow/badge/?version=latest)](https://flexflow.readthedocs.io/en/latest/?badge=latest)
+# flexflow-train
+[![clang-format Check](https://github.com/flexflow/flexflow-train/actions/workflows/clang-format-check.yml/badge.svg?branch=master)](https://github.com/flexflow/flexflow-train/actions/workflows/clang-format-check.yml)
+[![per-lib-checks](https://github.com/flexflow/flexflow-train/actions/workflows/per-lib-check.yml/badge.svg)](https://github.com/flexflow/flexflow-train/actions/workflows/per-lib-check.yml)
+[![shell-check](https://github.com/flexflow/flexflow-train/actions/workflows/shell-check.yml/badge.svg)](https://github.com/flexflow/flexflow-train/actions/workflows/shell-check.yml)
+[![Documentation Status](https://readthedocs.org/projects/flexflow/badge/?version=latest)](https://flexflow.readthedocs.io/en/latest/?badge=latest)
 
-FlexFlow is a deep learning framework that accelerates distributed DNN training by automatically searching for efficient parallelization strategies. FlexFlow provides a drop-in replacement for PyTorch and TensorFlow Keras. Running existing PyTorch and Keras programs in FlexFlow only requires [a few lines of changes to the program](https://flexflow.ai/keras).
+> [!WARNING]
+> The FlexFlow repository has been split into separate [flexflow-train](https://github.com/flexflow/flexflow-train) and [flexflow-serve](https://github.com/flexflow/flexflow-serve) repositories.
+> You are currently viewing [flexflow-train](https://github.com/flexflow/flexflow-train). 
+> For anything inference/serving-related, go to [flexflow-serve](https://github.com/flexflow/flexflow-serve). 
 
+FlexFlow is a deep learning framework that accelerates distributed DNN training by automatically searching for efficient parallelization strategies. 
+
+<!--
+FlexFlow provides a drop-in replacement for PyTorch and TensorFlow Keras. Running existing PyTorch and Keras programs in FlexFlow only requires [a few lines of changes to the program](https://flexflow.ai/keras).
+-->
+
+<!--
 ## Install FlexFlow
 To install FlexFlow from source code, please read the [instructions](INSTALL.md). If you would like to quickly try FlexFlow, we also provide pre-built Docker packages ([flexflow-cuda](https://github.com/flexflow/FlexFlow/pkgs/container/flexflow-cuda) with a CUDA backend, [flexflow-hip_rocm](https://github.com/flexflow/FlexFlow/pkgs/container/flexflow-hip_rocm) with a HIP-ROCM backend) with all dependencies pre-installed (N.B.: currently, the CUDA pre-built containers are only fully compatible with host machines that have CUDA 11.7 installed), together with [Dockerfiles](./docker) if you wish to build the containers manually. You can also use `conda` to install the FlexFlow Python package (coming soon).
 
@@ -67,10 +80,11 @@ Performance auto-tuning flags:
 * `--enable-parameter-parallel`: allow FlexFlow to explore parameter parallelism for performance auto-tuning. (By default FlexFlow only considers data and model parallelism.)
 * `--enable-attribute-parallel`: allow FlexFlow to explore attribute parallelism for performance auto-tuning. (By default FlexFlow only considers data and model parallelism.)
 For performance tuning related flags: see [performance autotuning](https://flexflow.ai/search).
+-->
 
 ## Contributing
 
-Please let us know if you encounter any bugs or have any suggestions by [submitting an issue](https://github.com/flexflow/flexflow/issues).
+Please let us know if you encounter any bugs or have any suggestions by [submitting an issue](https://github.com/flexflow/flexflow-train/issues).
 
 We welcome all contributions to FlexFlow from bug fixes to new features and extensions.
 

cmake/flexflow-utils.cmake

@@ -39,7 +39,7 @@ function(ff_set_cxx_properties target)
       CXX_EXTENSIONS NO
   )
   target_compile_options(${target}
-    PRIVATE $<$<COMPILE_LANGUAGE:CXX>:> # add C++ compile flags here
+    PRIVATE $<$<COMPILE_LANGUAGE:CXX>:> "-ffile-prefix-map=${CMAKE_SOURCE_DIR}=." # add C++ compile flags here
   )
 endfunction()
 

flake.lock

@@ -41,10 +41,13 @@
       mkShell = pkgs.mkShell.override {
         stdenv = pkgs.cudaPackages.backendStdenv;
       };
+
+      proj = proj-repo.packages.${system}.proj;
     in 
     {
       packages = {
         legion = pkgs.callPackage ./.flake/pkgs/legion.nix { };
+        ffdb = pkgs.callPackage ./.flake/pkgs/ffdb { inherit proj; };
         hpp2plantuml = pkgs.python3Packages.callPackage ./.flake/pkgs/hpp2plantuml.nix { };
         rapidcheckFull = pkgs.symlinkJoin {
           name = "rapidcheckFull";
@@ -138,7 +141,6 @@
               gh-markdown-preview
               shellcheck
               plantuml
-              gdb
               ruff
               compdb
               jq
@@ -158,6 +160,9 @@
               black
               toml
             ])
+            (with self.packages.${system}; [
+              ffdb
+            ])
           ];
         };
       };

flake.nix

@@ -2,6 +2,7 @@
 #define _FLEXFLOW_LIB_COMPILER_INCLUDE_COMPILER_COST_ESTIMATOR_COST_ESTIMATOR_H
 
 #include "compiler/cost_estimator/op_cost_estimate_key.dtg.h"
+#include "compiler/cost_estimator/op_cost_metrics.dtg.h"
 #include "compiler/cost_estimator/tensor_set_movement.dtg.h"
 #include "op-attrs/parallel_tensor_shape.dtg.h"
 #include "op-attrs/pcg_operator_attrs.dtg.h"
@@ -11,7 +12,7 @@
 namespace FlexFlow {
 
 struct ICostEstimator {
-  virtual float estimate_cost(OpCostEstimateKey const &) const = 0;
+  virtual OpCostMetrics estimate_cost(OpCostEstimateKey const &) const = 0;
   virtual float estimate_cost(TensorSetMovement const &) const = 0;
 
   ICostEstimator() = default;
@@ -23,7 +24,7 @@ struct ICostEstimator {
 CHECK_RC_COPY_VIRTUAL_COMPLIANT(ICostEstimator);
 
 struct CostEstimator {
-  float estimate_cost(OpCostEstimateKey const &k) const;
+  OpCostMetrics estimate_cost(OpCostEstimateKey const &) const;
   float estimate_cost(TensorSetMovement const &m) const;
 
   template <typename T, typename... Args>

lib/compiler/include/compiler/cost_estimator/cost_estimator.h

@@ -0,0 +1,18 @@
+namespace = "FlexFlow"
+name = "OpCostMetrics"
+features = [
+  "eq",
+  "fmt",
+  "hash",
+]
+
+includes = [
+]
+
+[[fields]]
+name = "runtime"
+type = "float"
+
+[[fields]]
+name = "memory"
+type = "size_t"