pp_dpm_set_power_profile_state was not implemented #63
Comments
|
Could you try with the vector_copy example in /opt/rocm/hsa/sample and see if you get the same error message? |
|
vector_copy passes all the tests, however, it returns the same error message as well. |
|
Could you send us the output of 'uname -a' to insure the correct kernel is installed? Also, is there any dmesg output that indicates this error? |
|
Here are the logs: uname -a: dmesg after the first execution of the code: dmesg for all of the executions after the second trial: |
|
The Invalid PPR device indicates that the kernel is accessing unknown memory pages. What is your hardware configuration? Are you using a discrete GPU, and if so, what is the version? If this is an APU, please send me the output of 'sudo dmidecode'. |
|
My APU is A10-8700P (Carrizo). Here is sudo dmidecode: dmidecode 3.0Getting SMBIOS data from sysfs. Handle 0x0000, DMI type 0, 24 bytes Handle 0x0001, DMI type 1, 27 bytes Handle 0x0002, DMI type 2, 17 bytes Handle 0x0003, DMI type 3, 24 bytes Handle 0x0004, DMI type 4, 42 bytes Handle 0x0005, DMI type 5, 19 bytes Handle 0x0006, DMI type 6, 12 bytes Handle 0x0007, DMI type 7, 19 bytes Handle 0x0008, DMI type 7, 19 bytes Handle 0x0009, DMI type 8, 9 bytes Handle 0x000A, DMI type 8, 9 bytes Handle 0x000B, DMI type 8, 9 bytes Handle 0x000C, DMI type 8, 9 bytes Handle 0x000D, DMI type 8, 9 bytes Handle 0x000E, DMI type 8, 9 bytes Handle 0x000F, DMI type 8, 9 bytes Handle 0x0010, DMI type 8, 9 bytes Handle 0x0011, DMI type 8, 9 bytes Handle 0x0012, DMI type 8, 9 bytes Handle 0x0013, DMI type 8, 9 bytes Handle 0x0014, DMI type 8, 9 bytes Handle 0x0015, DMI type 8, 9 bytes Handle 0x0016, DMI type 9, 17 bytes Handle 0x0017, DMI type 9, 17 bytes Handle 0x0018, DMI type 9, 17 bytes Handle 0x0019, DMI type 9, 17 bytes Handle 0x001A, DMI type 9, 17 bytes Handle 0x001B, DMI type 9, 17 bytes Handle 0x001C, DMI type 10, 6 bytes Handle 0x001D, DMI type 11, 5 bytes Handle 0x001E, DMI type 12, 5 bytes Handle 0x001F, DMI type 13, 22 bytes Handle 0x0020, DMI type 16, 23 bytes Handle 0x0021, DMI type 17, 40 bytes Handle 0x0022, DMI type 18, 23 bytes Handle 0x0023, DMI type 18, 23 bytes Handle 0x0024, DMI type 19, 31 bytes Handle 0x0025, DMI type 20, 35 bytes Handle 0x0026, DMI type 21, 7 bytes Handle 0x0027, DMI type 26, 22 bytes Handle 0x0028, DMI type 32, 20 bytes Handle 0x0029, DMI type 40, 18 bytes Handle 0x002A, DMI type 41, 11 bytes Handle 0x002B, DMI type 41, 11 bytes Handle 0x002C, DMI type 170, 78 bytes Handle 0x002D, DMI type 171, 39 bytes Handle 0x002E, DMI type 172, 27 bytes Handle 0xFEFF, DMI type 127, 4 bytes |
Hello,
Recently, I installed ROCm1.4 and tried to run my codes which could run on ROCm1.3.0.
I can compile my C++ code with HCC, and could run it in the first trial. At the same time I got the following message on the dmesg.
pp_dpm_set_power_profile_state was not implemented
From the second trial to run my executable, I got the segmentation error.
So, I am suspecting that the above message can be related to this segmentation error.
Does anyone know about it?
In my code, I am just using matrix calculation together with If statements in the parallel_for loop.
Best regards,
Nandinbaatar Tsog (Nabar)
The text was updated successfully, but these errors were encountered: