# VI ATOMP\_FRAME\_TRUNCATED Error When Running DLA-Based ONNX Model on Orin-X **URL:** \ **Category:** DRIVE AGX Orin General\ **Tags:** driveos-dl\ **Created:** [May 27, 2026, 10:20am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511 "2026-05-27T10:20:27Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![zaiwei](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@zaiwei](https://forums.developer.nvidia.com/u/zaiwei)\ **Post date:** [May 27, 2026, 10:20am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/1 "2026-05-27T10:20:27Z")
**DRIVE OS Version:** 6.0.10 **Issue Description:** VI ATOMP\_FRAME\_TRUNCATED Error When Running DLA-Based ONNX Model on Orin-X HI, NVIDIA We are running an ONNX model on the Orin platform. The model executes a specific FP16 high-channel 3x3 convolution workload and uses the DLA. We found that this triggers a VI error with the code `ATOMP_FRAME_TRUNCATED`. ![img_v3_02123_db3ba2fd-7620-4302-8182-266315cfc84g](https://global.discourse-cdn.com/nvidia/original/4X/d/e/d/ded304c402e2e180c7809843e24602e5c0760835.jpeg) ```auto /usr/src/tensorrt/bin/trtexec \ --onnx=models/special_vehicle_classifier/special_vehicle_classifier.onnx \ --int8 \ --fp16 \ --calib=models/special_vehicle_classifier/calibration_table \ --useDLACore=1 \ --allowGPUFallback \ --shapes=image_view:40x3x96x96,features:40x14x1x1,projected_lidar_view:40x3x96x96 \ --duration=3600 \ --warmUp=5000 ``` ```auto /** * Frame truncated writing to system memory. Maps to VI * ATOMP_FRAME_TRUNCATED event. This error typically indicates * memory back-pressure due to insufficient memory bandwidth * or an excessive memory access latency. * * This error sets @ref CAPTURE_STATUS_NOTIFY_BIT_ATOMP_FRAME_TRUNCATED * in @ref notify_bits. */ #define CAPTURE_STATUS_ATOMP_FRAME_TRUNCATED MK_U32(9) ``` Based on the comment, this error seems to be related to memory bandwidth or memory access latency. How should we understand this issue systematically? Are there any recommended solutions? Thanks in advance. Best regards, zaiwei ---
**Author:** ![SivaRamaKrishnaNV](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/sivaramakrishnanv/32/14043_2.png) [@SivaRamaKrishnaNV](https://forums.developer.nvidia.com/u/SivaRamaKrishnaNV)\ **Post date:** [May 27, 2026, 11:12am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/6 "2026-05-27T11:12:24Z")
Dear @zaiwei , Is this error encountered when running `trtexec` ? Could you share the log? ---
**Author:** ![zaiwei](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@zaiwei](https://forums.developer.nvidia.com/u/zaiwei)\ **Post date:** [May 28, 2026, 12:45am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/7 "2026-05-28T00:45:24Z")
trtexec is just our minimal offline reproduction solution. The initial discovery occurred during application runtime. Logs and reproduction methods are provided in the attachment. Thank you. [mre\_script\_nsys\_20260527\_202817.zip](https://forums.developer.nvidia.com/secure-uploads/nvidia/original/4X/f/9/a/f9aa44d654523d9b535ba12af5c4af10c3c0be36.zip) (79.0 MB) ---
**Author:** ![zaiwei](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@zaiwei](https://forums.developer.nvidia.com/u/zaiwei)\ **Post date:** [June 1, 2026, 2:06am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/8 "2026-06-01T02:06:36Z")
Hi [SivaRamaKrishna](https://forums.developer.nvidia.com/u/sivaramakrishnanv), Any update for this issue? ---
**Author:** ![SivaRamaKrishnaNV](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/sivaramakrishnanv/32/14043_2.png) [@SivaRamaKrishnaNV](https://forums.developer.nvidia.com/u/SivaRamaKrishnaNV)\ **Post date:** [June 1, 2026, 4:34am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/10 "2026-06-01T04:34:46Z")
Dear @zaiwei , From my understading, You are running nvsipl\_camera in parallel to trtexec. trtexec uses DLA with GPU fallback model enabled. Once you hit the issue you don’t see camera frames in nvsipl\_camera further or you notice few framedrops till trtexec runs? Does the model layer fallback to GPU? Do you notice same error when using DLA core 0? How frequently you notice this issue? ---
**Author:** ![zaiwei](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@zaiwei](https://forums.developer.nvidia.com/u/zaiwei)\ **Post date:** [June 7, 2026, 2:21am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/12 "2026-06-07T02:21:08Z")
> [@SivaRamaKrishnaNV](#): > > From my understading, You are running nvsipl\_camera in parallel to trtexec. trtexec uses DLA with GPU fallback model enabled. > Once you hit the issue you don’t see camera frames in nvsipl\_camera further or you notice few framedrops till trtexec runs? > Does the model layer fallback to GPU? Do you notice same error when using DLA core 0? How frequently you notice this issue? 1. The current model cannot disable GPU fallback. 2. While trtexec runs with the DLA1, sensor0–3 and sensor8–11 experience a gradual FPS drop down to 0 FPS. Once trtexec finishes, all sensors recover to normal frame rates. 3. Regarding the model layer, please refer to the attachment. 4. We do not reproduce this problem when using DLA core 0. ![img_v3_02128_88ec54f8-f63d-4c74-ba0c-e8cd02e79f1g](https://global.discourse-cdn.com/nvidia/original/4X/1/5/b/15b215a64e4627f8898942c981828df84b9bf152.jpeg) ---
**Author:** ![zaiwei](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@zaiwei](https://forums.developer.nvidia.com/u/zaiwei)\ **Post date:** [June 22, 2026, 3:18am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/14 "2026-06-22T03:18:19Z")
Hi [SivaRamaKrishna](https://forums.developer.nvidia.com/u/sivaramakrishnanv), Any update for this nvbug? ---
**Author:** ![SivaRamaKrishnaNV](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/sivaramakrishnanv/32/14043_2.png) [@SivaRamaKrishnaNV](https://forums.developer.nvidia.com/u/SivaRamaKrishnaNV)\ **Post date:** [June 22, 2026, 4:32am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/15 "2026-06-22T04:32:24Z")
Dear @zaiwei , Note that there are no releases for orin platform in devzone. Is it ok to use DLA core 0 for inference for GPU fallback? May I know if you have any other supported channel. ---
**Author:** ![carolyuu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/carolyuu/32/14043_2.png) [@carolyuu](https://forums.developer.nvidia.com/u/carolyuu)\ **Post date:** [July 2, 2026, 8:25pm UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/16 "2026-07-02T20:25:15Z")
Could you please provide any update for this topic? ---
**Author:** ![zaiwei](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@zaiwei](https://forums.developer.nvidia.com/u/zaiwei)\ **Post date:** [July 3, 2026, 12:13am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/17 "2026-07-03T00:13:24Z")
Yes, we plan to use DLA core 0 for inference. ---
**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\ **Post date:** [July 24, 2026, 5:44am UTC](https://forums.developer.nvidia.com/t/vi-atomp-frame-truncated-error-when-running-dla-based-onnx-model-on-orin-x/371511/20 "2026-07-24T05:44:29Z")
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.