Nvidia's poor RTX 50 compute test results due to missing 32-bit OpenCL support, says PassMark
A fix has been released by porting legacy OpenCL code to 64-bit.

After Nvidia pulled the plug on 32-bit CUDA support with CUDA 12.0 (and later), technologies built around this platform such as PhysX subsequently reached End Of Life. A new report from PassMark at X suggests that dropping legacy CUDA support extends its impact to older OpenCL code, written for 32-bit systems. This explains the lackluster performance in PassMark's Direct Compute benchmark, part of which contains 32-bit chunks of code; likely older libraries or modules.
Nvidia hasn't flipped the switch all of a sudden with one update. Legacy CUDA support has been gradually phased out through successive updates over the past few years. Notably, programs written with 32-bit CUDA in mind can still be run on RTX 40 or older hardware. On newer RTX 50 GPUs, older CUDA applications now fallback to the CPU, which is abysmally slower than the graphics card for parallel processing, as seen with PhysX. We suspect this is mostly a software limitation, and may be overcome by 32-bit to 64-bit translation layers, but don't expect anything official from Nvidia.
Found the explanation for RTX 5090 and 5080 low compute performance.Link: https://t.co/8Rq3K3Zw1PWe found out a few hours ago that nvidia removed OpenCL 32bit support. Seems it depended on CUDA 32bit. Which is also gone. We've been unable to buy a 5090 for testing (no stock… pic.twitter.com/gIp1HiOsJNFebruary 25, 2025
PassMark reports that Nvidia's decision to terminate 32-bit CUDA compatibility also affects legacy OpenCL code. While we don't have an official statement, the firm's tweet indicates that Nvidia has outright dropped 32-bit OpenCL support. Given the widespread Blackwell shortages, the PassMark team has been unable to procure an RTX 50 GPU for testing.
In fact, Nvidia's developer documentation for OpenCL still offers samples of code written for 32-bit environments. The code reportedly works fine on older RTX 40 (Ada Lovelace) GPUs, but throws a "non-obvious" error with RTX 50 hardware. It's fair to assume that dated OpenCL programs will never work on Blackwell and future GPUs, without necessary changes to the source code.
While the main PerformanceTest application from PassMark is compatible with modern systems, it still contains several sub-benchmarks that didn't require a 64-bit address space. For the benchmark to gauge performance properly, PassMark probably needed to recompile some of their kernels in 64-bit mode.
That's easier said than done, as older libraries and dependencies made with 32-bit systems in mind can quickly pile up depending on the age of your software. Likewise, this transition may require significant code changes when dealing with low-level operations and memory management.
The latest release of PerformanceTest has resolved these issues by updating required components to 64-bit, with the whole situation taking around a week or so to clear up. It's unlikely that entire codebases will shut down and compute software will cease to work, since most developers have slowly migrated towards 64-bit code over the years.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Hassam Nasir is a die-hard hardware enthusiast with years of experience as a tech editor and writer, focusing on detailed CPU comparisons and general hardware news. When he’s not working, you’ll find him bending tubes for his ever-evolving custom water-loop gaming rig or benchmarking the latest CPUs and GPUs just for fun.


















-
George³ If I had to count the problems with which the RTX 50 series launched, I would have a hard time, because I do not have a higher mathematical education. :anguished:Reply -
Pierce2623 So did Nvidia call em up like “your benchmark is under-representing our performance dammit!!!” ?Reply -
jp7189 A quick look through the Blackwell compatibility guide seems to have a bunch of caveats for applications using anything below 12.8, and there are quite a lot of ML apps out there that haven't been updated to v12 let alone 12.8.Reply
It would be interesting to see more ML benchmarks on 5000 series to see if there are performance issues. Lambda hasn't added tge 5000 series to their suite yet, but I'd guess that's likely because 5090's are still darn near non-existant. -
beyondlogic Oh what a shock dropping 32 bit physx would drop open cl 32 bit lol.Reply
They have killed 32 bit support essentially on this. -
truerock IMHO...Reply
I am glad to see obsolete technology go away. I think it is a "boat anchor" to new technology.
I do like to see virtual-PCs that support legacy tech. I wish somebody like Bill Gates would fund a few billion dollars to support legacy tech on virtual PCs. There are some pretty good virtual PCs out there... Oracle's, DOSBox, etc. Those are not as good as the original Microsoft Virtual PC 2004 and Virtual PC 2007 (which will not run on Windows 11) -
btspaniel I'm glad some journalists are doing some smart thinking for once. People shouldn't be blaming Nvidia for all these problems. Programmer should be updating and patching their games and software for modern hardware, We've been doing this forever on the emulation scene. We don't blame Nvidia or console manufacturers, we just inject custom updated programming that actually functions.Reply
P.S. how do I have 18,000 points for a website I never visit with less than five posts. -
JTWrenn I get that they want to push past 32 bit but....make a damn emulator at this point. How is this not just something that is handled in software for a transitionary period?Reply -
Mcnoobler
18000 points? Omg.btspaniel said:I'm glad some journalists are doing some smart thinking for once. People shouldn't be blaming Nvidia for all these problems. Programmer should be updating and patching their games and software for modern hardware, We've been doing this forever on the emulation scene. We don't blame Nvidia or console manufacturers, we just inject custom updated programming that actually functions.
P.S. how do I have 18,000 points for a website I never visit with less than five posts.
It isn't hard to tell people what they want to hear, and knock it out of the park with points. What is hard is being an individual thinker, and doing it even when found unpopular. -
kerberos_20
because you have old account, acient achievemt (7yr old) is 8k points, then ad some previous achivementsbtspaniel said:I'm glad some journalists are doing some smart thinking for once. People shouldn't be blaming Nvidia for all these problems. Programmer should be updating and patching their games and software for modern hardware, We've been doing this forever on the emulation scene. We don't blame Nvidia or console manufacturers, we just inject custom updated programming that actually functions.
P.S. how do I have 18,000 points for a website I never visit with less than five posts.