Compute Library v24.02.1

Author: Jenkins

CMakeLists.txt

@@ -28,7 +28,7 @@ cmake_minimum_required(VERSION 3.13 FATAL_ERROR)
 list(APPEND CMAKE_MESSAGE_CONTEXT ArmCompute)
 project(
   ArmCompute
-  VERSION 35.0.0
+  VERSION 35.0.1
   DESCRIPTION
     "The Arm Compute Library is a collection of low-level machine learning functions optimized for Arm® Cortex®-A CPU and Arm® Mali™ GPU architectures"
   LANGUAGES C CXX ASM)

README.md

@@ -9,7 +9,7 @@
  <img src="https://raw.githubusercontent.com/ARM-software/ComputeLibrary/gh-pages/ACL_logo.png"/><br><br>
 </div>
 
-# Compute Library ![](https://img.shields.io/badge/latest_release-24.02-green)
+# Compute Library ![](https://img.shields.io/badge/latest_release-24.02.1-green)
 
 
 The Compute Library is a collection of low-level machine learning functions optimized for Arm® Cortex®-A, Arm® Neoverse® and Arm® Mali™ GPUs architectures.<br>
@@ -37,7 +37,7 @@ Key Features:
 <br>
 
 ## Documentation
-[![Documentation](https://img.shields.io/badge/documentation-24.02-green)](https://arm-software.github.io/ComputeLibrary/latest)
+[![Documentation](https://img.shields.io/badge/documentation-24.02.1-green)](https://arm-software.github.io/ComputeLibrary/latest)
 
 > Note: The documentation includes the reference API, changelogs, build guide, contribution guide, errata, etc.
 
@@ -50,24 +50,24 @@ All the binaries can be downloaded from [here](https://github.com/ARM-software/C
 
 | Platform       | Operating System | Release archive (Download) |
 | -------------- | ---------------- | -------------------------- |
-| Raspberry Pi 4 | Linux® 32bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-armv7a-neon.tar.gz) |
-| Raspberry Pi 4 | Linux® 64bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon.tar.gz) |
-| Odroid N2      | Linux® 64bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon-cl.tar.gz) |
-| HiKey960       | Linux® 64bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon-cl.tar.gz) |
+| Raspberry Pi 4 | Linux® 32bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-armv7a-neon.tar.gz) |
+| Raspberry Pi 4 | Linux® 64bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon.tar.gz) |
+| Odroid N2      | Linux® 64bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon-cl.tar.gz) |
+| HiKey960       | Linux® 64bit      | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon-cl.tar.gz) |
 
 <br>
 
 | Architecture | Operating System | Release archive (Download) |
 | ------------ | ---------------- | -------------------------- |
-| armv7        | Linux®            | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-armv7a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-armv7a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-armv7a-neon-cl.tar.gz) |
-| arm64-v8a    | Android™          | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-android-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-android-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-android-arm64-v8a-neon-cl.tar.gz) |
-| arm64-v8a    | Linux®            | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8a-neon-cl.tar.gz) |
-| arm64-v8.2-a | Android™          | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-android-arm64-v8.2-a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-android-arm64-v8.2-a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-android-arm64-v8.2-a-neon-cl.tar.gz) |
-| arm64-v8.2-a | Linux®            | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8.2-a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8.2-a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02/arm_compute-v24.02-bin-linux-arm64-v8.2-a-neon-cl.tar.gz) |
+| armv7        | Linux®            | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-armv7a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-armv7a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-armv7a-neon-cl.tar.gz) |
+| arm64-v8a    | Android™          | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-android-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-android-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-android-arm64-v8a-neon-cl.tar.gz) |
+| arm64-v8a    | Linux®            | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8a-neon-cl.tar.gz) |
+| arm64-v8.2-a | Android™          | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-android-arm64-v8.2-a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-android-arm64-v8.2-a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-android-arm64-v8.2-a-neon-cl.tar.gz) |
+| arm64-v8.2-a | Linux®            | [![](https://img.shields.io/badge/build-neon-orange)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8.2-a-neon.tar.gz) [![](https://img.shields.io/badge/build-opencl-blue)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8.2-a-cl.tar.gz) [![](https://img.shields.io/badge/build-neon+cl-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/download/v24.02.1/arm_compute-v24.02.1-bin-linux-arm64-v8.2-a-neon-cl.tar.gz) |
 
 <br>
 
-Please refer to the following link for more pre-built binaries: [![](https://img.shields.io/badge/v24.02-bins-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/tag/v24.02)
+Please refer to the following link for more pre-built binaries: [![](https://img.shields.io/badge/v24.02.1-bins-yellowgreen)](https://github.com/ARM-software/ComputeLibrary/releases/tag/v24.02.1)
 
 Pre-build binaries are generated with the following security / good coding practices related flags:
 > -Wall, -Wextra, -Wformat=2, -Winit-self, -Wstrict-overflow=2, -Wswitch-default, -Woverloaded-virtual, -Wformat-security, -Wctor-dtor-privacy, -Wsign-promo, -Weffc++, -pedantic, -fstack-protector-strong

SConscript

@@ -31,10 +31,10 @@ import zlib
 import json
 import codecs
 
-VERSION = "v24.02"
+VERSION = "v24.02.1"
 LIBRARY_VERSION_MAJOR = 35
 LIBRARY_VERSION_MINOR =  0
-LIBRARY_VERSION_PATCH =  0
+LIBRARY_VERSION_PATCH =  1
 SONAME_VERSION = str(LIBRARY_VERSION_MAJOR) + "." + str(LIBRARY_VERSION_MINOR) + "." + str(LIBRARY_VERSION_PATCH)
 
 Import('env')

docs/Doxyfile

@@ -38,7 +38,7 @@ PROJECT_NAME           = "Compute Library"
 # could be handy for archiving the generated documentation or if some version
 # control system is used.
 
-PROJECT_NUMBER         = 24.02
+PROJECT_NUMBER         = 24.02.1
 
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a

docs/user_guide/release_version_and_change_log.dox

@@ -41,6 +41,10 @@ If there is more than one release in a month then an extra sequential number is
 
 @section S2_2_changelog Changelog
 
+v24.02.1 Public patch release
+ - Fix performance regression in fixed-format kernels
+ - Fix compile and runtime errors in arm_compute_validation for Windows on Arm(WoA)
+
 v24.02 Public major release
  - Replace template writer with compute kernel writer in dynamic fusion.
  - Performance optimizations:

src/common/cpuinfo/CpuInfo.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023 Arm Limited.
+ * Copyright (c) 2021-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -365,7 +365,12 @@ CpuInfo CpuInfo::build()
     isainfo.dot  = get_hw_capability("hw.optional.arm.FEAT_DotProd");
     CpuInfo info(isainfo, cpus_model);
     return info;
-#else                                            /* #elif defined(__aarch64__) && defined(__APPLE__) */
+#elif defined(__aarch64__) && defined(_WIN64)    /* #elif defined(__aarch64__) && defined(__APPLE__) */
+    CpuIsaInfo isainfo;
+    isainfo.neon = true;
+    CpuInfo info(isainfo, {CpuModel::GENERIC});
+    return info;
+#else                                            /* #elif defined(__aarch64__) && defined(_WIN64) */
     CpuInfo info(CpuIsaInfo(), {CpuModel::GENERIC});
     return info;
 #endif /* !defined(BARE_METAL) && !defined(__APPLE__) && !defined(__OpenBSD__) && (defined(__arm__) || defined(__aarch64__)) */

src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_s8q_nhwc_3x3_s1_output2x2_dot_depthfirst.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023 Arm Limited.
+ * Copyright (c) 2021-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -34,7 +34,7 @@
 namespace arm_conv {
 namespace depthwise {
 
-void a64_s8q_nhwc_3x3_s1_output2x2_dot_depthfirst_impl(unsigned int, const int8_t *const *, const int8_t *, const int32_t *, const arm_gemm::Requantize32&, const int32_t *, const int32_t *, int8_t *const *);
+void a64_s8q_nhwc_3x3_s1_output2x2_dot_depthfirst_impl(const unsigned int, const int8_t *const *const, const int8_t *, const int32_t *, const arm_gemm::Requantize32&, const int32_t *, const int32_t *, int8_t *const *const);
 
 class a64_s8q_nhwc_3x3_s1_output2x2_dot_depthfirst : public DepthwiseDepthfirstStrategy<int8_t, int8_t, int8_t, int32_t>
 {

src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_s8q_nhwc_3x3_s1_output2x2_mla_depthfirst.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023 Arm Limited.
+ * Copyright (c) 2021-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -34,7 +34,16 @@
 namespace arm_conv {
 namespace depthwise {
 
-void a64_s8q_nhwc_3x3_s1_output2x2_mla_depthfirst_impl(unsigned int, const int8_t *const *, const int8_t *, const int32_t *, const arm_gemm::Requantize32 &, const int32_t *, const int32_t *, int8_t *const *);
+void a64_s8q_nhwc_3x3_s1_output2x2_mla_depthfirst_impl(
+  const unsigned int,
+  const int8_t *const *const,
+  const int8_t *const,
+  const int32_t *const,
+  const arm_gemm::Requantize32 &,
+  const int32_t *const,
+  const int32_t *const,
+  int8_t *const *const
+);
 
 class a64_s8q_nhwc_3x3_s1_output2x2_mla_depthfirst : public DepthwiseDepthfirstStrategy<int8_t, int8_t, int8_t, int32_t>
 {

src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_s8q_nhwc_3x3_s1_output2x2_mla_depthfirst/generic.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023 Arm Limited.
+ * Copyright (c) 2021-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -45,7 +45,7 @@ void a64_s8q_nhwc_3x3_s1_output2x2_mla_depthfirst_impl(
 {
   struct Params
   {
-    long unsigned int n_channels;
+    uint64_t n_channels;
     const void *weights;
     const int32_t *bias;
     const arm_gemm::Requantize32 *requant;

src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_s8q_nhwc_3x3_s2_output2x2_mla_depthfirst.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2023 Arm Limited.
+ * Copyright (c) 2021-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -34,7 +34,17 @@
 namespace arm_conv {
 namespace depthwise {
 
-void a64_s8q_nhwc_3x3_s2_output2x2_mla_depthfirst_impl(unsigned int, const int8_t *const *, const int8_t *, const int32_t *, const arm_gemm::Requantize32 &, const int32_t *, const int32_t *, int8_t *const *);
+void a64_s8q_nhwc_3x3_s2_output2x2_mla_depthfirst_impl(
+  const unsigned int,
+  const int8_t *const *const,
+  const int8_t *const,
+  const int32_t *const,
+  const arm_gemm::Requantize32 &,
+  const int32_t *const,
+  const int32_t *const,
+  int8_t *const *const
+);
+
 
 class a64_s8q_nhwc_3x3_s2_output2x2_mla_depthfirst : public DepthwiseDepthfirstStrategy<int8_t, int8_t, int8_t, int32_t>
 {