Failed run tensorflow 2.3.0 with rocm 3.9.0(/src/external/hip-on-vdi/rocclr/hip_code_object.cpp:120: guarantee(false && "hipErrorNoBinaryForGpu: Coudn't find binary for current devices!"))

[zoran-liu]

/src/external/hip-on-vdi/rocclr/hip_code_object.cpp:120: guarantee(false && "hipErrorNoBinaryForGpu: Coudn't find binary for current devices!")

[xuhuisheng]

Duplicate of ROCm/ROCm#1269

[cjatin]

Which GPU are you running it on?

[zoran-liu]

Which GPU are you running it on?

RX 5700

[zoran-liu]

Duplicate of RadeonOpenCompute/ROCm#1269

I test rocspare with source code and get same error

[zoran-liu]

Agent 2

---

Name: gfx1010
Uuid: GPU-XX
Marketing Name: Navi 10 [Radeon RX 5600 OEM/5600 XT / 5700/5700 XT]
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 4096(0x1000)
Queue Max Size: 131072(0x20000)

[zoran-liu]

Ubuntu 20.04.1 LTS

[xuhuisheng]

@zoran-liu RX 5700 please refer this issue : ROCm/pytorch#718 (comment)

[2017040264]

I have the same error in ubuntu18.04.5 + Radeon Rx Vega10 Graphics + Rocm 3.10.

[ppanchad-amd]

Fixed in latest ROCm 6.0.2 (HIP 6.0.32831). Closing Ticket