NASP/cuda-samples
84
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-13 00:08:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
This is the release of the CUDA 13.3 samples, which include additions for CUDA Tile C++, and updated CCCL and Python samples.
This commit is contained in:
Dheemanth
2026-05-27 14:50:59 -07:00
committed by GitHub
parent aeab82ff30
commit b7c5481c55
150 changed files with 7977 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
python/2_CoreConcepts/greenContext/greenContext.py
View File

@@ -417,7 +417,7 @@ def run_critical_alone(
Establishes the pure compute time with every SM on the device available.
"""
stream = device.create_stream()
out = device.allocate(critical_n * 4)
out = device.allocate(critical_n * 4, stream=stream)
total_sm = device.resources.sm.sm_count
try:
opts = EventOptions(timing_enabled=True)
@@ -461,7 +461,7 @@ def run_baseline(
"""Both kernels on the primary context, two non-blocking streams."""
long_stream = device.create_stream()
critical_stream = device.create_stream()
out = device.allocate(critical_n * 4)
out = device.allocate(critical_n * 4, stream=critical_stream)
total_sm = device.resources.sm.sm_count
try:
return _run_one(
@@ -513,7 +513,7 @@ def run_green_context(
long_stream = ctx_long.create_stream()
critical_stream = ctx_crit.create_stream()
out = device.allocate(critical_n * 4)
out = device.allocate(critical_n * 4, stream=critical_stream)
return _run_one(
device,

2
python/2_CoreConcepts/greenContext/requirements.txt
View File

@@ -1,3 +1,3 @@
cuda-python>=13.0.0
cuda-core>=0.7.0
cuda-core>=1.0.0
numpy>=2.3.2