Change how CUDA runtime and capabilities are defined in Condor

update docstring

src/python/Utils/Utilities.py

@@ -10,6 +10,8 @@
 import sys
 from types import ModuleType, FunctionType
 from gc import get_referents
+from distutils.version import StrictVersion
+
 
 def lowerCmsHeaders(headers):
     """
@@ -295,3 +297,21 @@ def encodeUnicodeToBytesConditional(value, errors="ignore", condition=True):
     if condition:
         return encodeUnicodeToBytes(value, errors)
     return value
+
+
+def orderVersionList(versionList):
+    """
+    This function will order a list of version-style strings.
+    The order of precedence digits is from left to right. E.g.:
+      from: ["2.3.1", "1.2.3", "3.2.1", "1.3.2"]
+      to:   ["1.2.3", "1.3.2", "2.3.1", "3.2.1"]
+    :param versionList: list of strings
+    :return: an ordered list; or the initial data if different than list.
+
+    NOTE: implementation suggested in:
+    https://stackoverflow.com/questions/2574080/sorting-a-list-of-dot-separated-numbers-like-software-versions
+    """
+    if not isinstance(versionList, list):
+        return versionList
+    versionList.sort(key=StrictVersion)
+    return versionList

src/python/WMCore/BossAir/Plugins/BasePlugin.py

@@ -8,7 +8,7 @@
 from builtins import object, str, bytes
 from future.utils import viewvalues
 
-from Utils.Utilities import decodeBytesToUnicode
+from Utils.Utilities import decodeBytesToUnicode, orderVersionList
 from WMCore.WMException import WMException
 from WMCore.WMRuntime.Tools.Scram import ARCH_TO_OS, SCRAM_TO_ARCH
 
@@ -181,3 +181,31 @@ def scramArchtoRequiredArch(scramArch=None):
             archs = defaultArch
 
         return archs
+
+    @staticmethod
+    def cudaCapabilityToSingleVersion(capabilities=None):
+        """
+        Given a list of CUDA capabilities (with strings in a version style),
+        finds the smallest version required and convert it to a single integer
+        for comparison/job matchmaking purposes.
+        Version conversion formula is: (1000 * major + 10 * medium + minor)
+        :param capabilities: a list of string versions
+        :return: an integer with the version value; 0 in case of failure
+
+        For further details:
+        https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART____VERSION.html
+        """
+        defaultRes = 0
+        # get an ordered list of the versions and use the very first element
+        capabilities = orderVersionList(capabilities)
+        if not capabilities:
+            return defaultRes
+
+        smallestVersion = capabilities[0]
+        smallestVersion = smallestVersion.split(".")
+        # deal with versions like: "1", "1.2" and "1.2.3"
+        for _i in range(0, 3 - len(smallestVersion)):
+            smallestVersion.append(0)
+
+        intVersion = int(smallestVersion[0]) * 1000 + int(smallestVersion[1]) * 10 + int(smallestVersion[2])
+        return intVersion

src/python/WMCore/BossAir/Plugins/SimpleCondorPlugin.py

@@ -566,8 +566,11 @@ def getJobParameters(self, jobList):
             if job.get('gpuRequirements', None):
                 ad['My.GPUMemoryMB'] = str(job['gpuRequirements']['GPUMemoryMB'])
                 cudaCapabilities = ','.join(sorted(job['gpuRequirements']['CUDACapabilities']))
-                ad['My.CUDACapability'] = classad.quote(str(cudaCapabilities))
-                ad['My.CUDARuntime'] = classad.quote(job['gpuRequirements']['CUDARuntime'])
+                minimalCapability = self.cudaCapabilityToSingleVersion(job['gpuRequirements']['CUDACapabilities'])
+                ad['My.CUDACapability'] = classad.quote(str(minimalCapability))
+                ad['My.OriginalCUDACapability'] = classad.quote(str(cudaCapabilities))
+                cudaRuntime = ','.join(sorted(job['gpuRequirements']['CUDARuntime']))
+                ad['My.CUDARuntime'] = classad.quote(str(cudaRuntime))
             else:
                 ad['My.GPUMemoryMB'] = undefined
                 ad['My.CUDACapability'] = undefined