Update on "Support different NSE in batches of CSR and CSC tensors"

[ghstack-poisoned]
pytorch · Sep 11, 2022 · 27a47f1 · 27a47f1
2 parents cf6565a + 2e51cbb
commit 27a47f1
Show file tree

Hide file tree

Showing 396 changed files with 12,129 additions and 7,966 deletions.
diff --git a/.circleci/cimodel/data/simple/util/branch_filters.py b/.circleci/cimodel/data/simple/util/branch_filters.py
@@ -12,7 +12,7 @@
 
 RC_PATTERN = r"/v[0-9]+(\.[0-9]+)*-rc[0-9]+/"
 
-MAC_IOS_EXCLUSION_LIST = ["master", "nightly", "postnightly"]
+MAC_IOS_EXCLUSION_LIST = ["nightly", "postnightly"]
 
 
 def gen_filter_dict(

diff --git a/.circleci/config.yml b/.circleci/config.yml
diff --git a/.circleci/docker/common/install_ucc.sh b/.circleci/docker/common/install_ucc.sh
@@ -36,7 +36,7 @@ function install_ucc() {
   git submodule update --init --recursive
 
   ./autogen.sh
-  ./configure --prefix=$UCC_HOME --with-ucx=$UCX_HOME --with-nccl=no --with-cuda=$with_cuda
+  ./configure --prefix=$UCC_HOME --with-ucx=$UCX_HOME --with-cuda=$with_cuda
   time make -j
   sudo make install
 

diff --git a/.circleci/generate_config_yml.py b/.circleci/generate_config_yml.py
@@ -16,6 +16,7 @@
 import cimodel.data.simple.anaconda_prune_defintions
 import cimodel.data.simple.macos_definitions
 import cimodel.data.simple.upload_test_stats_definition
+import cimodel.data.simple.ios_definitions
 import cimodel.lib.miniutils as miniutils
 import cimodel.lib.miniyaml as miniyaml
 
@@ -144,6 +145,7 @@ def gen_build_workflows_tree():
         cimodel.data.simple.anaconda_prune_defintions.get_workflow_jobs,
         cimodel.data.simple.macos_definitions.get_new_workflow_jobs,
         cimodel.data.simple.upload_test_stats_definition.get_workflow_job,
+        cimodel.data.simple.ios_definitions.get_workflow_jobs,
     ]
     build_jobs = [f() for f in build_workflows_functions]
     build_jobs.extend(

diff --git a/.circleci/verbatim-sources/job-specs/job-specs-custom.yml b/.circleci/verbatim-sources/job-specs/job-specs-custom.yml
@@ -510,7 +510,40 @@
     macos:
       xcode: "12.5.1"
     steps:
-      - checkout
+      - run:
+          name: checkout with retry
+          command: |
+            checkout() {
+              set -ex
+              # Workaround old docker images with incorrect $HOME
+              # check https://github.com/docker/docker/issues/2968 for details
+              if [ "${HOME}" = "/" ]
+                then
+                export HOME=$(getent passwd $(id -un) | cut -d: -f6)
+              fi
+
+              mkdir -p ~/.ssh
+
+              echo 'github.com ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAq2A7hRGmdnm9tUDbO9IDSwBK6TbQa+PXYPCPy6rbTrTtw7PHkccKrpp0yVhp5HdEIcKr6pLlVDBfOLX9QUsyCOV0wzfjIJNlGEYsdlLJizHhbn2mUjvSAHQqZETYP81eFzLQNnPHt4EVVUh7VfDESU84KezmD5QlWpXLmvU31/yMf+Se8xhHTvKSCZIFImWwoG6mbUoWf9nzpIoaSjB+weqqUUmpaaasXVal72J+UX2B+2RPW3RcT0eOzQgqlJL3RKrTJvdsjE3JEAvGq3lGHSZXy28G3skua2SmVi/w4yCE6gbODqnTWlg7+wC604ydGXA8VJiS5ap43JXiUFFAaQ==
+              ' >> ~/.ssh/known_hosts
+
+              # use git+ssh instead of https
+              git config --global url."ssh://git@github.com".insteadOf "https://github.com" || true
+              git config --global gc.auto 0 || true
+
+              echo 'Cloning git repository'
+              mkdir -p '/Users/distiller/project'
+              cd '/Users/distiller/project'
+              git clone "$CIRCLE_REPOSITORY_URL" .
+              echo 'Checking out branch'
+              git checkout --force -B "$CIRCLE_BRANCH" "$CIRCLE_SHA1"
+              git --no-pager log --no-color -n 1 --format='HEAD is now at %h %s'
+            }
+
+            retry () {
+              $* || (sleep 1 && $*) || (sleep 2 && $*) || (sleep 4 && $*) || (sleep 8 && $*)
+            }
+            retry checkout
       - run_brew_for_ios_build
       - run:
           name: Run Fastlane

diff --git a/.github/actions/teardown-linux/action.yml b/.github/actions/teardown-linux/action.yml
@@ -16,7 +16,18 @@ runs:
       # Always hold for active ssh sessions
       shell: bash
       if: inputs.skip-wait-ssh == ''
-      run: .github/scripts/wait_for_ssh_to_drain.sh
+      run: |
+        set -eou pipefail
+
+        echo "Holding runner for 2 hours until all ssh sessions have logged out"
+        for _ in $(seq 1440); do
+            # Break if no ssh session exists anymore
+            if [ "$(who)" = "" ]; then
+              break
+            fi
+            echo "."
+            sleep 5
+        done
 
     - name: Kill containers, clean up images
       shell: bash

diff --git a/.github/ci_commit_pins/torchdynamo.txt b/.github/ci_commit_pins/torchdynamo.txt
@@ -1 +1 @@
-a2cc6466fc0793414e56674ea1d37d1c875b74bf
+ffd056dc1510bdfecafb689ed87601055694f3e6
diff --git a/.github/ci_commit_pins/vision.txt b/.github/ci_commit_pins/vision.txt
@@ -1 +1 @@
-9c3e2bf46bc49997679785d76b7d0a9fea0223c7
+a67cc87a33a3f713aebf5299bdeb2672c98e0bc5
diff --git a/.github/ci_commit_pins/xla.txt b/.github/ci_commit_pins/xla.txt
@@ -1 +1 @@
-b8688ee3c03120a15978844db6c4fa73eceb6594
+f00dd2f35ecf6455d97237d63c70c9c8ec190940
diff --git a/.github/scale-config.yml b/.github/scale-config.yml
diff --git a/.github/scripts/run_torchbench.py b/.github/scripts/run_torchbench.py
@@ -13,10 +13,12 @@
 # 1. Does not reuse the build artifact in other CI workflows
 # 2. CI jobs are serialized because there is only one worker
 import os
+import boto3  # type: ignore[import]
 import git  # type: ignore[import]
 import pathlib
 import argparse
 import subprocess
+from pathlib import Path
 
 from typing import List, Tuple
 
@@ -31,6 +33,25 @@
 direction: decrease
 timeout: 720
 tests:"""
+S3_BUCKET = "ossci-metrics"
+S3_PREFIX = "torchbench-pr-test"
+S3_URL_BASE = f"https://{S3_BUCKET}.s3.amazonaws.com/"
+
+class S3Client:
+    def __init__(self, bucket: str = S3_BUCKET, prefix: str = S3_PREFIX):
+        self.s3 = boto3.client('s3')
+        self.resource = boto3.resource('s3')
+        self.bucket = bucket
+        self.prefix = prefix
+
+    def upload_file(self, file_path: Path, filekey_prefix: str) -> None:
+        assert file_path.is_file(), f"Specified file path {file_path} does not exist or not file."
+        file_name = file_path.name
+        s3_key = f"{self.prefix}/{filekey_prefix}/{file_name}"
+        print(f"Uploading file {file_name} to S3 with key: {s3_key}")
+        self.s3.upload_file(str(file_path), self.bucket, s3_key)
+        # output the result URL
+        print(f"Uploaded the result file {file_name} to {S3_URL_BASE}{s3_key}")
 
 def gen_abtest_config(control: str, treatment: str, models: List[str]) -> str:
     d = {}
@@ -137,9 +158,21 @@ def run_userbenchmarks(pytorch_path: str, torchbench_path: str, base_sha: str, h
     print(f"Running torchbench userbenchmark command: {command}")
     subprocess.check_call(command, cwd=torchbench_path, env=env)
 
+def process_upload_s3(result_dir: str) -> None:
+    # validate result directory
+    result_dir_path = Path(result_dir)
+    assert result_dir_path.exists(), f"Specified result directory {result_dir} doesn't exist."
+    # upload all files to S3 bucket oss-ci-metrics
+    files = [x for x in result_dir_path.iterdir() if x.is_file()]
+    # upload file to S3 bucket
+    s3_client: S3Client = S3Client()
+    filekey_prefix = result_dir_path.name
+    for f in files:
+        s3_client.upload_file(f, filekey_prefix)
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Run TorchBench tests based on PR')
-    parser.add_argument('--pr-body', required=True, help="The file that contains body of a Pull Request")
+    parser.add_argument('--pr-body', help="The file that contains body of a Pull Request")
 
     subparsers = parser.add_subparsers(dest='command')
     # parser for setup the torchbench branch name env
@@ -151,6 +184,9 @@ def run_userbenchmarks(pytorch_path: str, torchbench_path: str, base_sha: str, h
     run_parser.add_argument('--pr-head-sha', required=True, type=str, help="The Pull Request head hash")
     run_parser.add_argument('--pytorch-path', required=True, type=str, help="Path to pytorch repository")
     run_parser.add_argument('--torchbench-path', required=True, type=str, help="Path to TorchBench repository")
+    # parser to upload results to S3
+    upload_parser = subparsers.add_parser("upload-s3")
+    upload_parser.add_argument('--result-dir', required=True, type=str, help="Path to benchmark output")
     args = parser.parse_args()
 
     if args.command == 'set-torchbench-branch':
@@ -181,6 +217,8 @@ def run_userbenchmarks(pytorch_path: str, torchbench_path: str, base_sha: str, h
         if not models and not userbenchmarks:
             print("Can't parse valid models or userbenchmarks from the pr body. Quit.")
             exit(-1)
+    elif args.command == 'upload-s3':
+        process_upload_s3(args.result_dir)
     else:
         print(f"The command {args.command} is not supported.")
         exit(-1)