[webgl] enabling WEBGL_USE_SHAPES_UNIFORMS results in model execution returning null values

user reported issue with my library and after a while it was traced down to WEBGL_USE_SHAPES_UNIFORMS
which i have enabled by default for over half a year now due to massive performance advantages

issue itself is that model execution shows no issues and it returns tensors in expected shape,
but tensor data is an array with all null values instead of expected float32 values

what is strange that on majority of systems there are no issues (plus i cannot reproduce locally)
and there is only single (quite small) affected model out of 10+ used

affected model

• https://vladmandic.github.io/human/models/faceres.json

very simple code reproduction (again, i cannot reproduce myself)
(it runs a model using predefined image input and checks output validity)

• https://vladmandic.github.io/human/test/issue-faceres.html?default: returns arrays with correct float values
• https://vladmandic.github.io/human/test/issue-faceres.html?uniforms: returns array with all null values

test has tfjs debug enabled and you can see all ops in the browser console

environment:

• tfjs: 3.20.0 (older versions are also affected)
• browser: chrome 104 and 105
• os: windows 10 pro

it’s reported on two different systems using different graphics adapters (AMD Radeon and nVidia RTX)
both affected systems report no issues looking at chrome://gpu and webgl v2 is working fine

only other thing worth noting is that user is using non-latin os locale

link to original issue: https://github.com/vladmandic/human/issues/291

[qjia7]

@vladmandic @shurshilov I have verified #6828 can fix this issue in my device. You can verify it in the next release or build from the source. If you still meet any problem, please feel free to reopen it or file a new bug. Thanks.

[qjia7]

More information: The current issue is not that enabling WEBGL_USE_SHAPES_UNIFORMS results in model execution returning null values anymore. But the faceres model couldn’t get correct result no matter WEBGL_USE_SHAPES_UNIFORMS is true or false.

In fact, the fix is more like a workaround. I don’t know why isnan_custom doesn’t work for packed binary. But it works for unpacked binary. I did a bunch of experiments for CHECK_NAN_SNIPPET_PACKED. But none of them work. Paste some findings so far in case someone may have more ideas. Tested GPU: Radeon ™ RX 480 Graphics

1. The incorrect isNaN coming from the input scalar b not a. If only check isnan_custom(a), we can get correct result.
2. Print b’s value instead of minimum’s result. The result seems no problem. I mean it’s expected b’s value.
3. Print vec4(isnan_custom(b))'s value. I also can’t see any abnormal. It’s all zero. But the incorrect result of minimum shows it should have a un-zero value to let the code go to result.xxx = isNaN.xxx ? NAN : result.xxx;
4. The most weird thing is that the incorrect value(0.5) is none of them in a(1.84), b(6.0) and NAN .