Release v13.3 of the CUDA samples with CUDA 13.3 Toolkit (#435)

This is the release of the CUDA 13.3 samples, which include additions for CUDA Tile C++, and updated CCCL and Python samples.

python/2_CoreConcepts/reduction/README.md

@@ -82,7 +82,7 @@ Two-Stage Reduction Strategy:
     - Elements per block: 512
     - Output: 32768 partial sums
   Stage 2: CPU final reduction
-    - Combine 32768 partial sums → 1 final result
+    - Combine 32768 partial sums -> 1 final result
 
 Compiling CUDA kernel...
   Kernel 'blockReduceKernel_float' compiled successfully

python/2_CoreConcepts/reduction/reduction.py

@@ -259,7 +259,7 @@ def run(
     print(f"    - Elements per block: {threads_per_block * 2}")
     print(f"    - Output: {num_blocks} partial sums")
     print("  Stage 2: CPU final reduction")
-    print(f"    - Combine {num_blocks} partial sums → 1 final result")
+    print(f"    - Combine {num_blocks} partial sums -> 1 final result")
 
     # Compile kernel
     print("\nCompiling CUDA kernel...")
@@ -320,7 +320,7 @@ def run(
 
         # cuda.core event elapsed time (end - start) is in milliseconds (CUDA API).
         stage1_times_ms = []
-        event_options = EventOptions(enable_timing=True)
+        event_options = EventOptions(timing_enabled=True)
         start_event = stream.device.create_event(options=event_options)
         end_event = stream.device.create_event(options=event_options)
         for _ in range(test_iterations):
@@ -342,7 +342,7 @@ def run(
 
         # Stage 2 (CPU)
         print("\n> Running Stage 2 (CPU final reduction)...")
-        # Device → Host: after stream sync, partial sums are visible on host.
+        # Device -> Host: after stream sync, partial sums are visible on host.
         stream.sync()
         with cp_stream:
             h_blockSums = cp.asnumpy(d_blockSums)

python/2_CoreConcepts/reduction/requirements.txt

@@ -2,7 +2,7 @@
 # Install with: pip install -r requirements.txt
 
 numpy>=2.3.2
-cuda-core>=0.6.0
+cuda-core>=1.0.0
 cuda-python>=13.0.0
 # Use cupy-cuda13x>=14.0.0 for cp.cuda.Stream.from_external(stream)
 cupy-cuda13x>=14.0.0