Docs: remove system_debugging.md

README.md

@@ -127,7 +127,6 @@ bash install-prerequisites.sh
 export GPU_ARCHS="gfx942"               # Example
 export GPU_ARCHS="gfx940;gfx941;gfx942" # Example
 
-cd ~/WORKSPACE/
 # Pick and run build commands in the docker container:
 # Build rocm-dev packages
 make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} rocm-dev

docs/how-to/system-debugging.md

@@ -1,68 +0,0 @@
----
-myst:
-  html_meta:
-    "description": "Learn more about common system-level debugging measures for ROCm."
-    "keywords": "env, var, sys, PCIe, troubleshooting, admin, error"
----
-
-# System debugging
-
-## ROCm language and system-level debug, flags, and environment variables
-
-Kernel options to avoid: the Ethernet port getting renamed every time you change graphics cards, `net.ifnames=0 biosdevname=0`
-
-## ROCr error code
-
-* 2 Invalid Dimension
-* 4 Invalid Group Memory
-* 8 Invalid (or Null) Code
-* 32 Invalid Format
-* 64 Group is too large
-* 128 Out of VGPRs
-* 0x80000000 Debug Options
-
-## Command to dump firmware version and get Linux kernel version
-
-`sudo cat /sys/kernel/debug/dri/1/amdgpu_firmware_info`
-
-`uname -a`
-
-## Debug flags
-
-Debug messages when developing/debugging base ROCm driver. You could enable the printing from `libhsakmt.so` by setting an environment variable, `HSAKMT_DEBUG_LEVEL`. Available debug levels are 3-7. The higher level you set, the more messages will print.
-
-* `export HSAKMT_DEBUG_LEVEL=3` : Only pr_err() prints.
-
-* `export HSAKMT_DEBUG_LEVEL=4` : pr_err() and pr_warn() print.
-
-* `export HSAKMT_DEBUG_LEVEL=5` : We currently do not implement “notice”. Setting to 5 is same as setting to 4.
-
-* `export HSAKMT_DEBUG_LEVEL=6` : pr_err(), pr_warn(), and pr_info print.
-
-* `export HSAKMT_DEBUG_LEVEL=7` : Everything including pr_debug prints.
-
-## ROCr level environment variables for debug
-
-`HSA_ENABLE_SDMA=0`
-
-`HSA_ENABLE_INTERRUPT=0`
-
-`HSA_SVM_GUARD_PAGES=0`
-
-`HSA_DISABLE_CACHE=1`
-
-## Turn off page retry on GFX9/Vega devices
-
-`sudo -s`
-
-`echo 1 > /sys/module/amdkfd/parameters/noretry`
-
-## HIP environment variables 3.x
-
-### OpenCL debug flags
-
-`AMD_OCL_WAIT_COMMAND=1 (0 = OFF, 1 = On)`
-
-## PCIe-debug
-
-For information on how to debug and profile HIP applications, see {doc}`hip:how-to/debugging`

docs/index.md

@@ -42,7 +42,6 @@ ROCm documentation is organized into the following categories:
 * [Use ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
 * [System optimization](./how-to/system-optimization/index.rst)
 * [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)
-* [System debugging](./how-to/system-debugging.md)
 * [Use advanced compiler features](./conceptual/compiler-topics.md)
 * [Set the number of CUs](./how-to/setting-cus)
 * [Troubleshoot BAR access limitation](./how-to/Bar-Memory.rst)

docs/sphinx/_toc.yml.in

@@ -109,7 +109,6 @@ subtrees:
     title: System optimization
   - file: how-to/gpu-performance/mi300x.rst
     title: AMD Instinct MI300X performance guides
-  - file: how-to/system-debugging.md
   - file: conceptual/compiler-topics.md
     title: Use advanced compiler features
     subtrees:
@@ -123,7 +122,7 @@ subtrees:
   - file: how-to/setting-cus
     title: Set the number of CUs
   - file: how-to/Bar-Memory.rst
-    title: Troubleshoot BAR access limitation  
+    title: Troubleshoot BAR access limitation
   - url: https://github.com/amd/rocm-examples
     title: ROCm examples
 

tools/rocm-build/ROCm.mk

@@ -115,7 +115,7 @@ $(call adddep,roctracer,${ASAN_DEP} rocr hip_on_rocclr)
 
 
 # rocm-dev points to all possible last finish components of Stage1 build.
-rocm-dev-components :=amd_smi_lib aqlprofile comgr dbgapi devicelibs hip_on_rocclr hipcc hipify_clang \
+rocm-dev-components :=amd_smi_lib aqlprofile aqlprofiletest comgr dbgapi devicelibs hip_on_rocclr hipcc hipify_clang \
 	lightning rocprofiler-compute opencl_on_rocclr openmp_extras rocm_bandwidth_test rocm_smi_lib \
 	rocm-cmake rocm-core rocm-gdb rocminfo rocprofiler-register rocprofiler-sdk rocprofiler-systems \
 	rocprofiler rocr rocr_debug_agent rocrsamples roctracer

tools/rocm-build/docker/ubuntu22/packages

@@ -60,6 +60,7 @@ libfile-find-rule-perl
 libgflags-dev
 libglew-dev
 libgmp-dev
+libgoogle-glog-dev
 libgtk2.0-dev
 libhdf5-serial-dev
 libjpeg-dev
@@ -89,6 +90,7 @@ libsuitesparse-dev
 libsystemd-dev
 libtinfo-dev
 libtool
+libunwind-dev
 liburi-encode-perl
 libva-dev
 libvirt-clients
@@ -96,6 +98,7 @@ libvirt-daemon-system
 libyaml-cpp-dev
 libzstd-dev
 llvm
+llvm-6.0-dev
 llvm-dev
 llvm-runtime
 mesa-common-dev
@@ -109,7 +112,8 @@ pigz
 pkg-config
 protobuf-compiler
 python-is-python3
-python3-pip-whl
+python-pip-whl
+python-yaml
 python3-dev
 python3-pip
 python3-venv

tools/rocm-build/docker/ubuntu24/install-prerequisites.sh

@@ -17,7 +17,7 @@ git --version
 
 # venv for python to be able to run pip3 without --break-system-packages
 python3 -m venv /opt/venv
-source /opt/venv/bin/activate
+
 pip3 install CppHeaderParser argparse lxml recommonmark jinja2==3.0.0 \
     websockets matplotlib numpy scipy minimal msgpack pytest sphinx joblib PyYAML rocm-docs-core cmake==3.25.2 pandas \
     myst-parser setuptools lit

tools/rocm-build/envsetup.sh

@@ -217,7 +217,7 @@ export RCCL_ROOT=$WORK_ROOT/rccl
 export ROCM_DBGAPI_ROOT=$WORK_ROOT/ROCdbgapi
 export ROCM_GDB_ROOT=$WORK_ROOT/ROCgdb
 # export ROCclr_ROOT=$WORK_ROOT/vdi
-export HIP_ON_ROCclr_ROOT=$WORK_ROOT/hip
+export HIP_ON_ROCclr_ROOT=$WORK_ROOT/HIP
 export HIPAMD_ROOT=$WORK_ROOT/hipamd
 export HIP_CATCH_TESTS_ROOT=$WORK_ROOT/hip-tests
 # export OPENCL_ON_ROCclr_ROOT=$WORK_ROOT/opencl-on-vdi