fix the cuda_bindings side

Author: ksimpson-work

cuda_bindings/benchmarks/kernels.py

@@ -7,7 +7,7 @@
 # is strictly prohibited.
 kernel_string = """\
 #define ITEM_PARAM(x, T) T x
-#define REP1(x, T)   , ITEM_PARAM(x, T)	
+#define REP1(x, T)   , ITEM_PARAM(x, T)
 #define REP2(x, T)   REP1(x##0, T)   REP1(x##1, T)
 #define REP4(x, T)   REP2(x##0, T)   REP2(x##1, T)
 #define REP8(x, T)   REP4(x##0, T)   REP4(x##1, T)

cuda_bindings/benchmarks/perf_test_utils.py

@@ -5,23 +5,24 @@
 # this software. Any use, reproduction, disclosure, or distribution of
 # this software and related documentation outside the terms of the EULA
 # is strictly prohibited.
+import numpy as np
 import pytest
+
 from cuda import cuda, cudart, nvrtc
-import numpy as np
 
 
 def ASSERT_DRV(err):
     if isinstance(err, cuda.CUresult):
         if err != cuda.CUresult.CUDA_SUCCESS:
-            raise RuntimeError("Cuda Error: {}".format(err))
+            raise RuntimeError(f"Cuda Error: {err}")
     elif isinstance(err, cudart.cudaError_t):
         if err != cudart.cudaError_t.cudaSuccess:
-            raise RuntimeError("Cudart Error: {}".format(err))
+            raise RuntimeError(f"Cudart Error: {err}")
     elif isinstance(err, nvrtc.nvrtcResult):
         if err != nvrtc.nvrtcResult.NVRTC_SUCCESS:
-            raise RuntimeError("Nvrtc Error: {}".format(err))
+            raise RuntimeError(f"Nvrtc Error: {err}")
     else:
-        raise RuntimeError("Unknown error type: {}".format(err))
+        raise RuntimeError(f"Unknown error type: {err}")
 
 
 @pytest.fixture

cuda_bindings/benchmarks/test_cupy.py

@@ -5,9 +5,10 @@
 # this software. Any use, reproduction, disclosure, or distribution of
 # this software and related documentation outside the terms of the EULA
 # is strictly prohibited.
-import pytest
 import ctypes
 
+import pytest
+
 # Always skip since cupy is not CTK 12.x yet
 skip_tests = True
 if not skip_tests:

cuda_bindings/benchmarks/test_launch_latency.py

@@ -5,12 +5,14 @@
 # this software. Any use, reproduction, disclosure, or distribution of
 # this software and related documentation outside the terms of the EULA
 # is strictly prohibited.
+import ctypes
+
 import pytest
+
 from cuda import cuda
-import ctypes
 
-from .perf_test_utils import ASSERT_DRV
 from .kernels import kernel_string
+from .perf_test_utils import ASSERT_DRV
 
 
 def launch(kernel, stream, args=(), arg_types=()):
@@ -310,7 +312,7 @@ def test_launch_latency_small_kernel_512_args_ctypes_with_packing(
     ASSERT_DRV(err)
 
     vals = []
-    for i in range(512):
+    for _i in range(512):
         err, p = cuda.cuMemAlloc(ctypes.sizeof(ctypes.c_int))
         ASSERT_DRV(err)
         vals.append(p)

cuda_bindings/benchmarks/test_numba.py

@@ -5,8 +5,8 @@
 # this software. Any use, reproduction, disclosure, or distribution of
 # this software and related documentation outside the terms of the EULA
 # is strictly prohibited.
-import pytest
 import numpy as np
+import pytest
 
 try:
     from numba import cuda

cuda_bindings/benchmarks/test_pointer_attributes.py

@@ -5,9 +5,11 @@
 # this software. Any use, reproduction, disclosure, or distribution of
 # this software and related documentation outside the terms of the EULA
 # is strictly prohibited.
+import random
+
 import pytest
+
 from cuda import cuda
-import random
 
 from .perf_test_utils import ASSERT_DRV
 

cuda_bindings/cuda/bindings/_version.py

@@ -11,12 +11,12 @@
 """Git implementation of _version.py."""
 
 import errno
+import functools
 import os
 import re
 import subprocess
 import sys
 from typing import Any, Callable, Dict, List, Optional, Tuple
-import functools
 
 
 def get_keywords() -> Dict[str, str]:
@@ -114,18 +114,18 @@ def run_command(
             if e.errno == errno.ENOENT:
                 continue
             if verbose:
-                print("unable to run %s" % dispcmd)
+                print(f"unable to run {dispcmd}")
                 print(e)
             return None, None
     else:
         if verbose:
-            print("unable to find command, tried %s" % (commands,))
+            print(f"unable to find command, tried {commands}")
         return None, None
     stdout = process.communicate()[0].strip().decode()
     if process.returncode != 0:
         if verbose:
-            print("unable to run %s (error)" % dispcmd)
-            print("stdout was %s" % stdout)
+            print(f"unable to run {dispcmd} (error)")
+            print(f"stdout was {stdout}")
         return None, process.returncode
     return stdout, process.returncode
 
@@ -158,8 +158,7 @@ def versions_from_parentdir(
 
     if verbose:
         print(
-            "Tried directories %s but none started with prefix %s"
-            % (str(rootdirs), parentdir_prefix)
+            f"Tried directories {str(rootdirs)} but none started with prefix {parentdir_prefix}"
         )
     raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
 
@@ -173,7 +172,7 @@ def git_get_keywords(versionfile_abs: str) -> Dict[str, str]:
     # _version.py.
     keywords: Dict[str, str] = {}
     try:
-        with open(versionfile_abs, "r") as fobj:
+        with open(versionfile_abs) as fobj:
             for line in fobj:
                 if line.strip().startswith("git_refnames ="):
                     mo = re.search(r'=\s*"(.*)"', line)
@@ -234,9 +233,9 @@ def git_versions_from_keywords(
         # "stabilization", as well as "HEAD" and "master".
         tags = {r for r in refs if re.search(r"\d", r)}
         if verbose:
-            print("discarding '%s', no digits" % ",".join(refs - tags))
+            print("discarding '{}', no digits".format(",".join(refs - tags)))
     if verbose:
-        print("likely tags: %s" % ",".join(sorted(tags)))
+        print("likely tags: {}".format(",".join(sorted(tags))))
     for ref in sorted(tags):
         # sorting will prefer e.g. "2.0" over "2.0rc1"
         if ref.startswith(tag_prefix):
@@ -247,7 +246,7 @@ def git_versions_from_keywords(
             if not re.match(r"\d", r):
                 continue
             if verbose:
-                print("picking %s" % r)
+                print(f"picking {r}")
             return {
                 "version": r,
                 "full-revisionid": keywords["full"].strip(),
@@ -291,7 +290,7 @@ def git_pieces_from_vcs(
     _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=not verbose)
     if rc != 0:
         if verbose:
-            print("Directory %s not under git control" % root)
+            print(f"Directory {root} not under git control")
         raise NotThisMethod("'git rev-parse --git-dir' returned error")
 
     # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
@@ -372,7 +371,7 @@ def git_pieces_from_vcs(
         mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
         if not mo:
             # unparsable. Maybe git-describe is misbehaving?
-            pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out
+            pieces["error"] = f"unable to parse git-describe output: '{describe_out}'"
             return pieces
 
         # tag
@@ -381,10 +380,7 @@ def git_pieces_from_vcs(
             if verbose:
                 fmt = "tag '%s' doesn't start with prefix '%s'"
                 print(fmt % (full_tag, tag_prefix))
-            pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % (
-                full_tag,
-                tag_prefix,
-            )
+            pieces["error"] = f"tag '{full_tag}' doesn't start with prefix '{tag_prefix}'"
             return pieces
         pieces["closest-tag"] = full_tag[len(tag_prefix) :]
 
@@ -521,13 +517,13 @@ def render_pep440_post(pieces: Dict[str, Any]) -> str:
             if pieces["dirty"]:
                 rendered += ".dev0"
             rendered += plus_or_dot(pieces)
-            rendered += "g%s" % pieces["short"]
+            rendered += "g{}".format(pieces["short"])
     else:
         # exception #1
         rendered = "0.post%d" % pieces["distance"]
         if pieces["dirty"]:
             rendered += ".dev0"
-        rendered += "+g%s" % pieces["short"]
+        rendered += "+g{}".format(pieces["short"])
     return rendered
 
 
@@ -546,15 +542,15 @@ def render_pep440_post_branch(pieces: Dict[str, Any]) -> str:
             if pieces["branch"] != "master":
                 rendered += ".dev0"
             rendered += plus_or_dot(pieces)
-            rendered += "g%s" % pieces["short"]
+            rendered += "g{}".format(pieces["short"])
             if pieces["dirty"]:
                 rendered += ".dirty"
     else:
         # exception #1
         rendered = "0.post%d" % pieces["distance"]
         if pieces["branch"] != "master":
             rendered += ".dev0"
-        rendered += "+g%s" % pieces["short"]
+        rendered += "+g{}".format(pieces["short"])
         if pieces["dirty"]:
             rendered += ".dirty"
     return rendered
@@ -653,7 +649,7 @@ def render(pieces: Dict[str, Any], style: str) -> Dict[str, Any]:
     elif style == "git-describe-long":
         rendered = render_git_describe_long(pieces)
     else:
-        raise ValueError("unknown style '%s'" % style)
+        raise ValueError(f"unknown style '{style}'")
 
     return {
         "version": rendered,

cuda_bindings/docs/source/conf.py

@@ -10,6 +10,7 @@
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 import os
+
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 

cuda_bindings/examples/0_Introduction/clock_nvrtc_test.py

@@ -6,10 +6,11 @@
 # this software and related documentation outside the terms of the EULA
 # is strictly prohibited.
 import numpy as np
-from cuda import cuda
 from common import common
 from common.helper_cuda import checkCudaErrors, findCudaDevice
 
+from cuda import cuda
+
 clock_nvrtc = """\
 extern "C" __global__  void timedReduction(const float *hinput, float *output, clock_t *timer)
 {
@@ -115,7 +116,7 @@ def main():
         avgElapsedClocks += timer[i + NUM_BLOCKS] - timer[i]
 
     avgElapsedClocks = avgElapsedClocks / NUM_BLOCKS
-    print("Average clocks/block = {}".format(avgElapsedClocks))
+    print(f"Average clocks/block = {avgElapsedClocks}")
 
 
 if __name__ == "__main__":

cuda_bindings/examples/0_Introduction/simpleCubemapTexture_test.py

@@ -7,13 +7,15 @@
 # is strictly prohibited.
 import ctypes
 import math
-import numpy as np
 import sys
 import time
-from cuda import cuda, cudart
+
+import numpy as np
 from common import common
 from common.helper_cuda import checkCudaErrors, findCudaDevice
 
+from cuda import cuda, cudart
+
 simpleCubemapTexture = """\
 extern "C"
 __global__ void transformKernel(float *g_odata, int width, cudaTextureObject_t tex)
@@ -90,18 +92,11 @@ def main():
     # Get number of SMs on this GPU
     deviceProps = checkCudaErrors(cudart.cudaGetDeviceProperties(devID))
     print(
-        "CUDA device [{}] has {} Multi-Processors SM {}.{}".format(
-            deviceProps.name,
-            deviceProps.multiProcessorCount,
-            deviceProps.major,
-            deviceProps.minor,
-        )
+        f"CUDA device [{deviceProps.name}] has {deviceProps.multiProcessorCount} Multi-Processors SM {deviceProps.major}.{deviceProps.minor}"
     )
     if deviceProps.major < 2:
         print(
-            "{} requires SM 2.0 or higher for support of Texture Arrays.  Test will exit...".format(
-                sSDKname
-            )
+            "Test requires SM 2.0 or higher for support of Texture Arrays.  Test will exit..."
         )
         sys.exit()
 
@@ -175,9 +170,7 @@ def main():
     dimGrid.z = 1
 
     print(
-        "Covering Cubemap data array of {}~3 x {}: Grid size is {} x {}, each block has 8 x 8 threads".format(
-            width, num_layers, dimGrid.x, dimGrid.y
-        )
+        f"Covering Cubemap data array of {width}~3 x {num_layers}: Grid size is {dimGrid.x} x {dimGrid.y}, each block has 8 x 8 threads"
     )
 
     kernelHelper = common.KernelHelper(simpleCubemapTexture, devID)
@@ -222,11 +215,9 @@ def main():
 
     checkCudaErrors(cudart.cudaDeviceSynchronize())
     stop = time.time()
-    print("Processing time: {:.3f} msec".format(stop - start))
+    print(f"Processing time: {stop - start:.3f} msec")
     print(
-        "{:.2f} Mtexlookups/sec".format(
-            cubemap_size / ((stop - start + 1) / 1000.0) / 1e6
-        )
+        f"{cubemap_size / ((stop - start + 1) / 1000.0) / 1e6:.2f} Mtexlookups/sec"
     )
 
     # Allocate mem for the result on host side