search

ROCm / rocm-install-on-linux

https://rocm.docs.amd.com/projects/install-on-linux/en/latest/
MIT License
8 stars 8 forks source link

[Issue]: rocm-smi --setpoweroverdrive does allow lowering the power usage anymore #256

Closed acaleechurn closed 6 days ago

acaleechurn commented 1 month ago

Problem Description

rocm-smi --setpoweroverdrive 200 does allow lowering the power usage anymore. This was functional (6.1.2) prior to upgrading. We would lower the temperature significantly with minimal impact on training times.

Operating System

22.04.4 LTS (Jammy Jellyfish)

CPU

AMD EPYC 7402P

GPU

AMD Instinct MI100

ROCm Version

ROCm 6.2.0

ROCm Component

amdsmi, rocm_smi_lib

Steps to Reproduce

acaleechurn@svr-ph-ml01:~$ rocm-smi --setpoweroverdrive 200

============================ ROCm System Management Interface ============================ ================================ Set GPU Power OverDrive ================================= ERROR: GPU[0] : Unable to set Power OverDrive ERROR: GPU[0] : Value cannot be less than: 290W ERROR: GPU[1] : Unable to set Power OverDrive ERROR: GPU[1] : Value cannot be less than: 290W ERROR: GPU[2] : Unable to set Power OverDrive ERROR: GPU[2] : Value cannot be less than: 290W

================================== End of ROCm SMI Log =================================== acaleechurn@svr-ph-ml01:~$

(Optional for Linux users) Output of /opt/rocm/bin/rocminfo --support

ROCk module version 6.8.5 is loaded =====================
HSA System Attributes
=====================
Runtime Version: 1.14 Runtime Ext Version: 1.6 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE
System Endianness: LITTLE
Mwaitx: DISABLED DMAbuf Support: YES

==========
HSA Agents
==========

Agent 1

Name: AMD EPYC 7402P 24-Core Processor
Uuid: CPU-XX
Marketing Name: AMD EPYC 7402P 24-Core Processor
Vendor Name: CPU
Feature: None specified
Profile: FULL_PROFILE
Float Round Mode: NEAR
Max Queue Number: 0(0x0)
Queue Min Size: 0(0x0)
Queue Max Size: 0(0x0)
Queue Type: MULTI
Node: 0
Device Type: CPU
Cache Info:
L1: 32768(0x8000) KB
Chip ID: 0(0x0)
ASIC Revision: 0(0x0)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 2800
BDFID: 0
Internal Node ID: 0
Compute Unit: 24
SIMDs per CU: 0
Shader Engines: 0
Shader Arrs. per Eng.: 0
WatchPts on Addr. Ranges:1
Memory Properties:
Features: None Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: FINE GRAINED
Size: 263781388(0xfb8fc0c) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 2
Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED Size: 263781388(0xfb8fc0c) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 3
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 263781388(0xfb8fc0c) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
ISA Info:

Agent 2

Name: gfx908
Uuid: GPU-e336f877361f1399
Marketing Name: AMD Instinct MI100
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 1
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
L2: 8192(0x2000) KB
Chip ID: 29580(0x738c)
ASIC Revision: 2(0x2)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 1502
BDFID: 35328
Internal Node ID: 1
Compute Unit: 120
SIMDs per CU: 4
Shader Engines: 8
Shader Arrs. per Eng.: 1
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Memory Properties:
Features: KERNEL_DISPATCH Fast F16 Operation: TRUE
Wavefront Size: 64(0x40)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension: x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 40(0x28)
Max Work-item Per CU: 2560(0xa00)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension: x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 67
SDMA engine uCode:: 18
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 33538048(0x1ffc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 33538048(0x1ffc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 3
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension: x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension: x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
FBarrier Max Size: 32

Agent 3

Name: gfx908
Uuid: GPU-c13bf411f2279689
Marketing Name: AMD Instinct MI100
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 2
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
L2: 8192(0x2000) KB
Chip ID: 29580(0x738c)
ASIC Revision: 2(0x2)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 1502
BDFID: 17920
Internal Node ID: 2
Compute Unit: 120
SIMDs per CU: 4
Shader Engines: 8
Shader Arrs. per Eng.: 1
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Memory Properties:
Features: KERNEL_DISPATCH Fast F16 Operation: TRUE
Wavefront Size: 64(0x40)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension: x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 40(0x28)
Max Work-item Per CU: 2560(0xa00)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension: x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 67
SDMA engine uCode:: 18
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 33538048(0x1ffc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 33538048(0x1ffc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 3
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension: x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension: x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
FBarrier Max Size: 32

Agent 4

Name: gfx908
Uuid: GPU-34985558949eb94a
Marketing Name: AMD Instinct MI100
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 3
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
L2: 8192(0x2000) KB
Chip ID: 29580(0x738c)
ASIC Revision: 2(0x2)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 1502
BDFID: 1280
Internal Node ID: 3
Compute Unit: 120
SIMDs per CU: 4
Shader Engines: 8
Shader Arrs. per Eng.: 1
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Memory Properties:
Features: KERNEL_DISPATCH Fast F16 Operation: TRUE
Wavefront Size: 64(0x40)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension: x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 40(0x28)
Max Work-item Per CU: 2560(0xa00)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension: x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 67
SDMA engine uCode:: 18
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 33538048(0x1ffc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 33538048(0x1ffc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 3
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension: x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension: x 4294967295(0xffffffff)
y 4294967295(0xffffffff)
z 4294967295(0xffffffff)
FBarrier Max Size: 32
Done

Additional Information

OS: NAME="Ubuntu" VERSION="22.04.4 LTS (Jammy Jellyfish)" CPU: model name : AMD EPYC 7402P 24-Core Processor GPU: Name: AMD EPYC 7402P 24-Core Processor Marketing Name: AMD EPYC 7402P 24-Core Processor Name: gfx908 Marketing Name: AMD Instinct MI100 Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Name: gfx908 Marketing Name: AMD Instinct MI100 Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Name: gfx908 Marketing Name: AMD Instinct MI100 Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- (acal-ml) acaleechurn@svr-ph-ml01:~$

acaleechurn commented 1 month ago

Cleaning up the install and running a multi-version install with the kernel-mode-driver from 6.1.2 works as expected. Upgrading to 6.2.0 breaks the functionality.

acaleechurn@svr-ph-ml01:~$ rocm-smi --setpoweroverdrive 200

============================ ROCm System Management Interface ============================ ================================ Set GPU Power OverDrive ================================= GPU[0] : Successfully set power to: 200W GPU[1] : Successfully set power to: 200W GPU[2] : Successfully set power to: 200W

================================== End of ROCm SMI Log ===================================

NAME="Ubuntu" VERSION="22.04.4 LTS (Jammy Jellyfish)" CPU: model name : AMD EPYC 7402P 24-Core Processor GPU: Name: AMD EPYC 7402P 24-Core Processor Marketing Name: AMD EPYC 7402P 24-Core Processor Name: gfx908 Marketing Name: AMD Instinct MI100 Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Name: gfx908 Marketing Name: AMD Instinct MI100 Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- Name: gfx908 Marketing Name: AMD Instinct MI100 Name: amdgcn-amd-amdhsa--gfx908:sramecc+:xnack- acaleechurn@svr-ph-ml01:~$ rocminfo --support ROCk module version 6.7.0 is loaded

HSA System Attributes

Runtime Version: 1.14 Runtime Ext Version: 1.6 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED DMAbuf Support: YES

harkgill-amd commented 1 week ago

Hi @acaleechurn, I see https://github.com/ROCm/rocm_smi_lib/issues/190 was also opened. Let's continue to use that ticket for correspondence on this issue.