From 9c70865fad75342da341ee6ee876920381a36bf7 Mon Sep 17 00:00:00 2001 From: Jason Andrews Date: Fri, 26 Sep 2025 16:23:56 -0500 Subject: [PATCH] spelling and tag updates --- .wordlist.txt | 139 +++++++++++++++++- content/learning-paths/automotive/_index.md | 9 +- .../embedded-and-microcontrollers/_index.md | 3 +- .../laptops-and-desktops/_index.md | 10 +- .../mobile-graphics-and-gaming/_index.md | 7 +- .../servers-and-cloud-computing/_index.md | 22 ++- .../irq-tuning-guide/checking.md | 2 +- .../3_llama.cpp_annotation.md | 4 +- .../4_analyze_token_prefill_decode.md | 2 +- .../5_operator_deepdive.md | 2 +- 10 files changed, 177 insertions(+), 23 deletions(-) diff --git a/.wordlist.txt b/.wordlist.txt index 79c3f66d0f..9606eb651b 100644 --- a/.wordlist.txt +++ b/.wordlist.txt @@ -4812,4 +4812,141 @@ learnt lof BalenaOS balenaCloud - +MX +ARMFp +AndroidDemo +ApacheBench +ArmHalideAndroidDemo +Autoscheduler +BGR +BVM +BenchmarkBubbleSort +BenchmarkQuickSort +Botspot +BoundaryConditions +BubbleSort +ByteBuffer +DGGML +DNQZJ +DTLB +EPYC +ETag +EVEX +Esc +FuseAll +FuseBlurAndThreshold +GGG +GOPATH +GOROOT +GTK +GetByteArrayElements +Golang +Golang’s +HWC +Halide +Halide’s +ImageParam +Istio +KEDA +Kedify +Kedify’s +LLC +LLE +MPix +NIC’s +Netty +NoRuntime +OpenBMC’s +Parallelization +QCOW +QuickSort +RDom +RGBRGBRGB +RRR +RamFB +Recomputation +ReleaseByteArrayElements +Remmina +Roubalik +SAXPY +ScaledObject +Scaler +SetByteArrayRegion +SoL +Sor +Sysoev +TinyRPS +UFW +VLA +VTOR +VirtualService +WindowsOnArm +XMM +YMM +YUV +ZMM +Zbynek +adaptively +allocs +apiKey +armhalideandroiddemo +autounattend +autowiring +benchmarkHttpResponse +benchmem +blurThresholdImage +bvm +clusterName +coroutine +createBitmapFromGrayBytes +cv +extractGrayScaleBytes +fallbacks +firstlogin +golang +gosort +goweb +halide +httpd +inBytes +inlines +inputBuffer +insturction +jbyteArray +keda +kedify +keypress +kts +llmexport +loadImageFromAssets +microarchitectures +minikube +oOer +orgId +outputArray +outputBuffer +parallelization +parallelize +parallelized +parallelizes +preallocation +precomputing +qcow +recomputation +reconfig +reconversion +refetching +req +scaler +scalers +sprintf +stdev +thresholded +underperformed +underperforms +unvectorized +uop +walkthrough +warmups +xo +yi \ No newline at end of file diff --git a/content/learning-paths/automotive/_index.md b/content/learning-paths/automotive/_index.md index 97fb52787c..43a8e96e60 100644 --- a/content/learning-paths/automotive/_index.md +++ b/content/learning-paths/automotive/_index.md @@ -12,10 +12,10 @@ title: Automotive weight: 4 subjects_filter: - Containers and Virtualization: 3 -- Performance and Architecture: 5 +- Performance and Architecture: 6 operatingsystems_filter: - Baremetal: 1 -- Linux: 7 +- Linux: 8 - macOS: 1 - RTOS: 1 tools_software_languages_filter: @@ -23,10 +23,11 @@ tools_software_languages_filter: - Arm Zena CSS: 1 - C: 2 - C++: 1 -- Clang: 2 +- Clang: 3 - DDS: 1 - Docker: 2 -- GCC: 2 +- FVP: 1 +- GCC: 3 - Python: 2 - Raspberry Pi: 1 - ROS 2: 3 diff --git a/content/learning-paths/embedded-and-microcontrollers/_index.md b/content/learning-paths/embedded-and-microcontrollers/_index.md index 945b031b43..e5d9c4f74d 100644 --- a/content/learning-paths/embedded-and-microcontrollers/_index.md +++ b/content/learning-paths/embedded-and-microcontrollers/_index.md @@ -45,11 +45,12 @@ tools_software_languages_filter: - CMSIS-DSP: 1 - CMSIS-Toolbox: 3 - CNN: 1 +- Computer Vision: 1 - Containerd: 1 - DetectNet: 1 - Docker: 10 - DSTREAM: 2 -- Edge AI: 1 +- Edge AI: 2 - Edge Impulse: 1 - ExecuTorch: 3 - FastAPI: 1 diff --git a/content/learning-paths/laptops-and-desktops/_index.md b/content/learning-paths/laptops-and-desktops/_index.md index 25ff68127d..b0c3d43298 100644 --- a/content/learning-paths/laptops-and-desktops/_index.md +++ b/content/learning-paths/laptops-and-desktops/_index.md @@ -9,13 +9,13 @@ maintopic: true operatingsystems_filter: - Android: 2 - ChromeOS: 2 -- Linux: 33 +- Linux: 34 - macOS: 9 -- Windows: 44 +- Windows: 45 subjects_filter: - CI-CD: 5 - Containers and Virtualization: 7 -- Migration to Arm: 28 +- Migration to Arm: 29 - ML: 2 - Performance and Architecture: 27 subtitle: Create and migrate apps for power efficient performance @@ -28,6 +28,7 @@ tools_software_languages_filter: - Arm Performance Libraries: 2 - Arm64EC: 1 - Assembly: 1 +- Bash: 1 - C: 8 - C#: 6 - C++: 11 @@ -48,6 +49,7 @@ tools_software_languages_filter: - Intrinsics: 1 - JavaScript: 2 - Kubernetes: 1 +- KVM: 1 - Linux: 1 - LLM: 1 - LLVM: 2 @@ -61,7 +63,9 @@ tools_software_languages_filter: - OpenCV: 1 - perf: 4 - Python: 6 +- QEMU: 1 - Qt: 2 +- RDP: 1 - Remote.It: 1 - RME: 1 - Runbook: 18 diff --git a/content/learning-paths/mobile-graphics-and-gaming/_index.md b/content/learning-paths/mobile-graphics-and-gaming/_index.md index aae0dcbb19..0ba3f637ac 100644 --- a/content/learning-paths/mobile-graphics-and-gaming/_index.md +++ b/content/learning-paths/mobile-graphics-and-gaming/_index.md @@ -9,7 +9,7 @@ key_ip: - Mali maintopic: true operatingsystems_filter: -- Android: 31 +- Android: 32 - Linux: 30 - macOS: 14 - Windows: 14 @@ -17,7 +17,7 @@ subjects_filter: - Gaming: 6 - Graphics: 6 - ML: 12 -- Performance and Architecture: 34 +- Performance and Architecture: 35 subtitle: Optimize Android apps and build faster games using cutting-edge Arm tech title: Mobile, Graphics, and Gaming tools_software_languages_filter: @@ -26,7 +26,7 @@ tools_software_languages_filter: - Android: 4 - Android NDK: 2 - Android SDK: 1 -- Android Studio: 10 +- Android Studio: 11 - Arm Development Studio: 1 - Arm Mobile Studio: 1 - Arm Performance Studio: 3 @@ -38,6 +38,7 @@ tools_software_languages_filter: - CCA: 1 - Clang: 12 - CMake: 1 +- Coding: 1 - Docker: 1 - ExecuTorch: 1 - Frame Advisor: 1 diff --git a/content/learning-paths/servers-and-cloud-computing/_index.md b/content/learning-paths/servers-and-cloud-computing/_index.md index c42dd243cc..c17a248304 100644 --- a/content/learning-paths/servers-and-cloud-computing/_index.md +++ b/content/learning-paths/servers-and-cloud-computing/_index.md @@ -8,7 +8,7 @@ key_ip: maintopic: true operatingsystems_filter: - Android: 3 -- Linux: 175 +- Linux: 177 - macOS: 13 - Windows: 14 pinned_modules: @@ -19,11 +19,11 @@ pinned_modules: - migration subjects_filter: - CI-CD: 7 -- Containers and Virtualization: 31 +- Containers and Virtualization: 32 - Databases: 17 - Libraries: 9 - ML: 31 -- Performance and Architecture: 71 +- Performance and Architecture: 72 - Storage: 1 - Web: 12 subtitle: Optimize cloud native apps on Arm for performance and cost @@ -72,7 +72,7 @@ tools_software_languages_filter: - Capstone: 1 - CCA: 8 - Clair: 1 -- Clang: 12 +- Clang: 13 - ClickBench: 1 - ClickHouse: 1 - CMake: 1 @@ -89,7 +89,7 @@ tools_software_languages_filter: - Fortran: 1 - FunASR: 1 - FVP: 7 -- GCC: 24 +- GCC: 25 - gdb: 1 - Geekbench: 1 - Generative AI: 12 @@ -106,21 +106,27 @@ tools_software_languages_filter: - Google Cloud: 2 - Google Test: 1 - HammerDB: 1 +- Helm: 1 - Herd7: 1 - Hugging Face: 11 - InnoDB: 1 - Intrinsics: 1 - iPerf3: 1 +- ipmitool: 1 - Java: 4 - JAX: 1 - JMH: 1 - Kafka: 1 +- KEDA: 1 +- Kedify: 1 - Keras: 1 -- Kubernetes: 10 +- KleidiAI: 1 +- Kubernetes: 11 - Libamath: 1 - libbpf: 1 - Linaro Forge: 1 - Litmus7: 1 +- llama.cpp: 1 - Llama.cpp: 2 - LLM: 10 - llvm-mca: 1 @@ -135,6 +141,7 @@ tools_software_languages_filter: - mpi: 1 - MySQL: 9 - NEON: 7 +- Neoverse: 1 - Networking: 1 - Nexmark: 1 - NGINX: 4 @@ -142,12 +149,14 @@ tools_software_languages_filter: - Ollama: 1 - ONNX Runtime: 1 - OpenBLAS: 1 +- OpenBMC: 1 - OpenJDK 21: 2 - OpenShift: 1 - Orchard Core: 1 - PAPI: 1 - perf: 6 - PostgreSQL: 4 +- Profiling: 1 - Python: 31 - PyTorch: 9 - QEMU: 1 @@ -188,6 +197,7 @@ tools_software_languages_filter: - wrk2: 2 - x265: 1 - YCSB: 1 +- Yocto/BitBake: 1 - zlib: 1 - ZooKeeper: 1 weight: 1 diff --git a/content/learning-paths/servers-and-cloud-computing/irq-tuning-guide/checking.md b/content/learning-paths/servers-and-cloud-computing/irq-tuning-guide/checking.md index 3eee3c2d17..f9a798b797 100644 --- a/content/learning-paths/servers-and-cloud-computing/irq-tuning-guide/checking.md +++ b/content/learning-paths/servers-and-cloud-computing/irq-tuning-guide/checking.md @@ -69,4 +69,4 @@ done ### Saving these changes -Any changes you make to IRQs will be reset at reboot. You will need to change your systems settings to make your changes permanant. +Any changes you make to IRQs will be reset at reboot. You will need to change your systems settings to make your changes permanent. diff --git a/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/3_llama.cpp_annotation.md b/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/3_llama.cpp_annotation.md index b1ed11a127..85ddc43038 100644 --- a/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/3_llama.cpp_annotation.md +++ b/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/3_llama.cpp_annotation.md @@ -26,7 +26,7 @@ For installation guidance, refer to the [Streamline installation guide](https:// Clone the gator repository that matches your Streamline version and build the `Annotation support library`. -The installation step is depends on your developement machine. +The installation step is depends on your development machine. For Arm native build, you can use following insturction to install the packages. For other machine, you need to set up the cross compiler environment by install [aarch64 gcc compiler toolchain](https://developer.arm.com/downloads/-/arm-gnu-toolchain-downloads). @@ -121,7 +121,7 @@ Finally, add an annotation marker inside the main loop: } ``` -A string is added to the Annotation Marker to record the position of input tokens and numbr of tokens to be processed. +A string is added to the Annotation Marker to record the position of input tokens and number of tokens to be processed. ### Step 3: Build llama-cli diff --git a/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/4_analyze_token_prefill_decode.md b/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/4_analyze_token_prefill_decode.md index 6af4230564..d33d989fa9 100644 --- a/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/4_analyze_token_prefill_decode.md +++ b/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/4_analyze_token_prefill_decode.md @@ -113,7 +113,7 @@ By monitoring other PMU events, Backend Stall Cycles and Backend Stall Cycles du We can see that at Prefill stage, Backend Stall Cycles due to Memory stall are only about 10% of total Backend Stall Cycles. However, at Decode stage, Backend Stall Cycles due to Memory stall are around 50% of total Backend Stall Cycles. All those PMU event counters indicate that it is compute-bound at Prefill stage and memory-bound at Decode stage. -Now, let us further profile the code execution with Streamline. In the ‘Call Paths’ view of Streamline, we can see the percentage of running time of functions that are orginized in form of call stack. +Now, let us further profile the code execution with Streamline. In the ‘Call Paths’ view of Streamline, we can see the percentage of running time of functions that are organized in form of call stack. ![text#center](images/annotation_prefill_call_stack.png "Figure 12. Call stack") In the ‘Functions’ view of Streamline, we can see the overall percentage of running time of functions. diff --git a/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/5_operator_deepdive.md b/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/5_operator_deepdive.md index 295169777d..fd1cb948dc 100644 --- a/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/5_operator_deepdive.md +++ b/content/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/5_operator_deepdive.md @@ -82,7 +82,7 @@ for (int node_n = 0; node_n < cgraph->n_nodes && atomic_load_explicit(&tp->abort ### Step 2: Add Tensor Shape Info (Optional) -You can also add information of the shape and size of source tensor by replace sprintf funcation as follow: +You can also add information of the shape and size of source tensor by replace sprintf function as follow: ```c sprintf(printf_buf,"%s %s %d_%d_%d %d_%d_%d", node->name, ggml_get_name(node), \