CHANGELOG.md update for ROCm 4.1 (#1263)

CHANGELOG.md

@@ -1,8 +1,18 @@
 # Change Log for Tensile
 
-## [Tensile 4.24.0 for ROCm 4.0.0]
+## [Tensile 4.26.0 for ROCm 4.1.0]
 ### Added
-- ROCm 4.0 TargetID support in Tensile; source kernels force xnack=OFF
+- Make messagepack python dependency optional
+- TensileCreateLibraryFiles: auto create target for build time lib generation
+- Tensile cluster tuning tool
+- Framework for filtering solutions
+- Workflow for manually editing Kernels
+- Tuning client design doc
+- MatrixInstruction for general int8
+- Tensile integration test for TensileCreateLibrary
+- Trig float and random narrow init patterns for new client
+- Summation dimension mirroring (contributed by timlathy & Slimakanzer)
+- ROCm 4.1 TargetID support in Tensile; source kernels force xnack=OFF
 - Tensile/Utilities/merge.py revamp for merging logic yaml files
   - now merge.py requires python3
   - add `-v` verbosity levels (up to 2)
@@ -13,6 +23,11 @@
 - Support for High Precision Accumulate FP16/BF16 In FP32 Out
 - CHANGELOG.md
 
+### Optimizations
+- Refine PersistentKernel: support PKn1, EPS, optimize LW-vmcnt and sMagicDiv2
+
 ### Fixed
+- targets to clang-offload-bundler updated to use hipv4 prefix when appropriate
+- Fix bugs of tail-loop branch label, and LR addr restore
 - locateExe in Tensile/Common.py looks in defaultPath first
 - Honor $ENV{ROCM_PATH} to support relocatable ROCm location