Update

Author: shwina

c/parallel/src/clangjit/compiler.cpp

@@ -377,7 +377,6 @@ class CUDACompiler::Impl
     arg_strings.push_back("-D__CLANGJIT_DEVICE_COMPILATION__=1");
     arg_strings.push_back("-DNDEBUG");
     arg_strings.push_back("-DCCCL_DISABLE_CTK_COMPATIBILITY_CHECK");
-    arg_strings.push_back("-D_CCCL_ENABLE_FREESTANDING=1");
     arg_strings.push_back("-DCCCL_DISABLE_FP16_SUPPORT=1");
     arg_strings.push_back("-DCCCL_DISABLE_BF16_SUPPORT=1");
     arg_strings.push_back("-DCCCL_DISABLE_NVTX=1");
@@ -777,13 +776,10 @@ class CUDACompiler::Impl
     arg_strings.push_back("-D__CLANGJIT_DEVICE_COMPILATION__=1");
     arg_strings.push_back("-DNDEBUG");
     arg_strings.push_back("-DCCCL_DISABLE_CTK_COMPATIBILITY_CHECK");
-    arg_strings.push_back("-D_CCCL_ENABLE_FREESTANDING=1");
     arg_strings.push_back("-DCCCL_DISABLE_FP16_SUPPORT=1");
     arg_strings.push_back("-DCCCL_DISABLE_BF16_SUPPORT=1");
     arg_strings.push_back("-DCCCL_DISABLE_NVTX=1");
     arg_strings.push_back("-DCCCL_DISABLE_EXCEPTIONS=1");
-    arg_strings.push_back("-DCCCL_DISABLE_FP16_SUPPORT=1");
-    arg_strings.push_back("-DCCCL_DISABLE_BF16_SUPPORT=1");
     arg_strings.push_back("-fdeprecated-macro");
     arg_strings.push_back("-fcxx-exceptions");
     arg_strings.push_back("-fexceptions");

ci/matrix.yaml

@@ -65,8 +65,13 @@ workflows:
     - {jobs: ['test'], project: 'cccl_c_parallel', ctk: '13.X', cxx: ['gcc13', 'msvc'], gpu: ['rtx2080', 'l4', 'h100']}
     # RTX PRO 6000 coverage (limited due to small number of runners):
     - {jobs: ['test'], project: 'cccl_c_parallel', ctk: '13.X', cxx: ['gcc13'], gpu: ['rtxpro6000']}
-    # c.parallel with ClangJIT (one gcc, one msvc to track build times before adding caching)
-    - {jobs: ['test'], project: 'cccl_c_parallel_clangjit', ctk: '13.X', cxx: ['gcc13', 'msvc'], gpu: 'rtx2080'}
+    # c.parallel with ClangJIT
+    #
+    # For now, this is a separate job run for Linux/CUDA13.
+    # Eventually we will want building with ClangJIT to be the
+    # default, and will do it across the entire matrix. Currently
+    # blocked on libnvfatbin availability on Windows containers, and for CUDA <12.4.
+    - {jobs: ['test'], project: 'cccl_c_parallel_clangjit', ctk: '13.X', cxx: ['gcc13'], gpu: 'rtx2080'}
     # c.experimental.stf-- pinned to gcc13 to match python
     - {jobs: ['test'], project: 'cccl_c_stf', ctk: '12.X', cxx: 'gcc13', gpu: ['rtx2080']}
     - {jobs: ['test'], project: 'cccl_c_stf', ctk: '13.X', cxx: 'gcc13', gpu: ['rtx2080', 'l4', 'h100']}