Nvidia's poor RTX 50 compute test results due to missing 32-bit OpenCL support, says PassMark

RTX 5090 Gallery Shot
(Image credit: Nvidia)

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.

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.

TOPICS
Hassam Nasir
Contributing Writer

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.

Read more
GeForce RTX 5090 Founders Edition
PhysX feature unlocked for RTX 5090 with RTX 3050 'helper' to enable full performance
PhysX
PhysX quietly retired on RTX 50 series GPUs: Nvidia ends 32-bit CUDA app support
Nvidia GeForce RTX 5090 Founders Edition card photos and unboxing
Nvidia's RTX 50-series drivers feel half-baked, focus too much on MFG
RTX 40 series
RTX 40 GPU owners suffering from BSODs and crashes complain about Nvidia's RTX 50 focus
GeForce RTX 5090 Founders Edition
Defective RTX 5080 takes up to 11% performance hit in gaming — Larger impact at higher resolutions
GeForce RTX 5090 Founders Edition
RTX 5080 with missing ROPs takes a 12% performance hit in synthetic benchmark
Latest in GPUs
WireView Pro 90 degrees
Thermal Grizzly's WireView Pro GPU power measuring utility gets a 90-degree adapter revision
Nvidia Ada Lovelace and GeForce RTX 40-Series
Analyst claims Nvidia's gaming GPUs could use Intel Foundry's 18A node in the future
RX 9070 XT Sapphire
Lisa Su says Radeon RX 9070-series GPU sales are 10X higher than its predecessors — for the first week of availability
RTX 5070, RX 9070 XT, Arc B580
These are the best GPU 'deals' based on real-world scalper pricing and our FPS per dollar test results
Zotac Gaming GeForce RTX 5090 AMP Extreme Infinity
Zotac raises RTX 5090 prices by 20% and seemingly eliminates MSRP models
project-g-assist-nvidia-geforce-rtx-ogimage
Nvidia releases public G-Assist in latest App to provide in-game AI assistance — also introduces DLSS custom scaling factors
Latest in News
Inspur
US expands China trade blacklist, closes susidiary loopholes
WireView Pro 90 degrees
Thermal Grizzly's WireView Pro GPU power measuring utility gets a 90-degree adapter revision
Qualcomm
Qualcomm launches global antitrust campaign against Arm — accuses Arm of restricting access to technology
Nvidia Ada Lovelace and GeForce RTX 40-Series
Analyst claims Nvidia's gaming GPUs could use Intel Foundry's 18A node in the future
Core Ultra 200S CPU
An Arrow Lake refresh may still be in the cards with only K and KF models, claims leaker
RX 9070 XT Sapphire
Lisa Su says Radeon RX 9070-series GPU sales are 10X higher than its predecessors — for the first week of availability
  • 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
  • yngndrw
    I think they should retain the OpenCl 32bit tests, as it's still in use.
    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.

    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.
    Reply
  • beyondlogic
    Oh what a shock dropping 32 bit physx would drop open cl 32 bit lol.

    They have killed 32 bit support essentially on this.
    Reply
  • truerock
    IMHO...

    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)
    Reply
  • 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.

    P.S. how do I have 18,000 points for a website I never visit with less than five posts.
    Reply
  • 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
    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.
    18000 points? Omg.

    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.
    Reply
  • kerberos_20
    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.
    because you have old account, acient achievemt (7yr old) is 8k points, then ad some previous achivements
    Reply