Merge pull request #128 from casparvl/support_cc_100_and_above

Don't assume that a CUDA CC only contains two numbers, we want to also support CC100, CC120, etc

Author: bedroge

EESSI-extend-easybuild.eb

@@ -96,12 +96,24 @@ sysroot = os.getenv("EESSI_EPREFIX")
 -- Check if we have GPU capabilities and configure CUDA compute capabilities
 eessi_accelerator_target = os.getenv("EESSI_ACCELERATOR_TARGET")
 if (eessi_accelerator_target ~= nil) then
-  cuda_compute_capability = string.match(eessi_accelerator_target, "^accel/nvidia/cc([0-9][0-9])$")
+  cuda_compute_capability = string.match(eessi_accelerator_target, "^accel/nvidia/cc([0-9]+)$")
   if (cuda_compute_capability ~= nil) then
-    easybuild_cuda_compute_capabilities = cuda_compute_capability:sub(1, 1) ..  "." .. cuda_compute_capability:sub(2, 2)
+    -- The last digit should be the minor version, insert a dot in the one-but-last position
+    major_version = cuda_compute_capability:sub(1, #cuda_compute_capability - 1)
+    minor_version = cuda_compute_capability:sub(#cuda_compute_capability)
+    easybuild_cuda_compute_capabilities = string.format("%s.%s", major_version, minor_version)
   else
     LmodError("Incorrect value for $EESSI_ACCELERATOR_TARGET: " .. eessi_accelerator_target)
   end
+
+  -- If architectures are 9.0, 10.0 or 12.0, enable architecture or family-specific optimizations
+  if easybuild_cuda_compute_capabilities == '9.0' then
+    easybuild_cuda_compute_capabilities = '9.0a'
+  elseif easybuild_cuda_compute_capabilities == '10.0' then
+    easybuild_cuda_compute_capabilities = '10.0f'
+  elseif easybuild_cuda_compute_capabilities == '12.0' then
+    easybuild_cuda_compute_capabilities = '12.0f'
+  end
 end
 
 -- Some environment variables affect behaviour, let's gather them once

init/eessi_archdetect.sh

@@ -165,11 +165,11 @@ accelpath() {
     # If EESSI_ACCELERATOR_TARGET_OVERRIDE is set, use it
     log "DEBUG" "accelpath: Override variable set as '$EESSI_ACCELERATOR_TARGET_OVERRIDE' "
     if [ ! -z $EESSI_ACCELERATOR_TARGET_OVERRIDE ]; then
-        if [[ "$EESSI_ACCELERATOR_TARGET_OVERRIDE" =~ ^accel/nvidia/cc[0-9][0-9]$ ]]; then
+        if [[ "$EESSI_ACCELERATOR_TARGET_OVERRIDE" =~ ^accel/nvidia/cc[0-9]+$ ]]; then
             echo ${EESSI_ACCELERATOR_TARGET_OVERRIDE}
             return 0
         else
-            log "ERROR" "Value of \$EESSI_ACCELERATOR_TARGET_OVERRIDE should match 'accel/nvidia/cc[0-9[0-9]', but it does not: '$EESSI_ACCELERATOR_TARGET_OVERRIDE'"
+            log "ERROR" "Value of \$EESSI_ACCELERATOR_TARGET_OVERRIDE should match 'accel/nvidia/cc[0-9]+', but it does not: '$EESSI_ACCELERATOR_TARGET_OVERRIDE'"
         fi
         return 0
     fi