search

ROCm / ROCR-Runtime

ROCm Platform Runtime: ROCr a HPC market enhanced HSA based runtime
https://rocm.docs.amd.com/projects/ROCR-Runtime/en/latest/
Other
224 stars 109 forks source link

[Issue]: HwlConvertChipFamily assert failed on gfx1033 #262

Open cgmb opened 3 days ago

cgmb commented 3 days ago

Problem Description

There seems to be a failing assertion in libhsa-runtime64 when running on the Valve Steam Deck (gfx1033). This behaviour was observed in ROCm 5.7.1 and ROCm 6.1.2, but was not seen in ROCm 5.2.3.

This assertion occurs when running the the test suites for all ROCm libraries. For example, when running hipsolver-test:

hipSOLVER version 1.7.0.
hipsolver-test: ./src/image/addrlib/src/gfx10/gfx10addrlib.cpp:1071: virtual rocr::Addr::ChipFamily rocr::Addr::V2::Gfx10Lib::HwlConvertChipFamily(unsigned int, unsigned int): Assertion `false' failed.

That corresponds to the "Unknown chip revision" assertion in the code:

        case FAMILY_VGH:
            if (ASICREV_IS_VANGOGH(chipRevision))
            {
                m_settings.supportRbPlus   = 1;
                m_settings.dccUnsup3DSwDis = 0;
            }
            else
            {
                ADDR_ASSERT(!"Unknown chip revision");
            }
            break;

https://ci.rocm.debian.net/packages/h/hipsolver/unstable/amd64+gfx1033/43073/

Operating System

Debian 13

CPU

AMD Custom APU 0405

GPU

AMD Custom GPU 0405

ROCm Version

ROCm 6.1.0

ROCm Component

No response

Steps to Reproduce

No response

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

Running rocminfo and expecting GPU information
ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.1
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 Custom APU 0405                
  Uuid:                    CPU-XX                             
  Marketing Name:          AMD Custom APU 0405                
  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:            8                                  
  SIMDs per CU:            0                                  
  Shader Engines:          0                                  
  Shader Arrs. per Eng.:   0                                  
  WatchPts on Addr. Ranges:1                                  
  Features:                None
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: FINE GRAINED        
      Size:                    15190292(0xe7c914) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    15190292(0xe7c914) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 3                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    15190292(0xe7c914) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
*******                  
Agent 2                  
*******                  
  Name:                    gfx1033                            
  Uuid:                    GPU-XX                             
  Marketing Name:          AMD Custom GPU 0405                
  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:                      1024(0x400) KB                     
  Chip ID:                 5695(0x163f)                       
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   0                                  
  BDFID:                   1024                               
  Internal Node ID:        1                                  
  Compute Unit:            8                                  
  SIMDs per CU:            2                                  
  Shader Engines:          1                                  
  Shader Arrs. per Eng.:   1                                  
  WatchPts on Addr. Ranges:4                                  
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      TRUE                               
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  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:: 118                                
  SDMA engine uCode::      70                                 
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    7595144(0x73e488) KB               
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS:                     
      Size:                    7595144(0x73e488) KB               
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1033         
      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

No response

cgmb commented 3 days ago

There was a similar problem on Rembrandt (gfx1035), which I addressed with a patch. It doesn't seem to have helped with gfx1033, though.

diff --git a/src/image/image_manager_kv.cpp b/src/image/image_manager_kv.cpp
index 5d3750e..8c3f2ec 100755
--- a/src/image/image_manager_kv.cpp
+++ b/src/image/image_manager_kv.cpp
@@ -97,6 +97,11 @@ hsa_status_t ImageManagerKv::Initialize(hsa_agent_t agent_handle) {
       agent_, static_cast<hsa_agent_info_t>(HSA_AMD_AGENT_INFO_ASIC_FAMILY_ID), &family_type_);
   assert(status == HSA_STATUS_SUCCESS);

+  uint32_t chip_revision;
+  status = HSA::hsa_agent_get_info(
+      agent_, static_cast<hsa_agent_info_t>(HSA_AMD_AGENT_INFO_ASIC_REVISION), &chip_revision);
+  assert(status == HSA_STATUS_SUCCESS);
+
   HsaGpuTileConfig tileConfig = {0};
   unsigned int tc[40];
   unsigned int mtc[40];
@@ -125,7 +130,7 @@ hsa_status_t ImageManagerKv::Initialize(hsa_agent_t agent_handle) {
   }

   addr_create_input.chipFamily = family_type_;
-  addr_create_input.chipRevision = 0;  // TODO(bwicakso): find how to get this.
+  addr_create_input.chipRevision = chip_revision;

   ADDR_CREATE_FLAGS create_flags = {};
   create_flags.value = 0;