aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--docs/00_introduction.dox14
1 files changed, 14 insertions, 0 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox
index 9c8eaf273..ca9e7e353 100644
--- a/docs/00_introduction.dox
+++ b/docs/00_introduction.dox
@@ -248,9 +248,14 @@ v19.08 Public major release
- CLGEMMTranspose1xWKernel / CLGEMMTranspose1xW
- CLWidthConcatenateLayer
- New NEON kernels / functions:
+ - @ref NEAbsLayer
- @ref NECast
+ - @ref NEElementwisePower
+ - @ref NELogLayer
- @ref NELSTMLayerQuantized
+ - @ref NENegLayer
- @ref NEPReluLayer
+ - @ref NESinLayer
- @ref NEBatchConcatenateLayerKernel
- @ref NEDepthToSpaceLayerKernel / @ref NEDepthToSpaceLayer
- @ref NEDepthwiseConvolutionLayerNativeKernel
@@ -258,8 +263,13 @@ v19.08 Public major release
- @ref NEMeanStdDevNormalizationKernel / @ref NEMeanStdDevNormalizationLayer
- @ref NESpaceToDepthLayerKernel / @ref NESpaceToDepthLayer
- New OpenCL kernels / functions:
+ - @ref CLAbsLayer
+ - @ref CLElementwisePower
+ - @ref CLLogLayer
- @ref CLLSTMLayerQuantized
+ - @ref CLNegLayer
- @ref CLPReluLayer
+ - @ref CLSinLayer
- @ref CLBatchConcatenateLayerKernel
- @ref CLDepthToSpaceLayerKernel / @ref CLDepthToSpaceLayer
- @ref CLGEMMLowpMatrixMultiplyNativeKernel
@@ -271,6 +281,9 @@ v19.08 Public major release
- neon_opticalflow
- cl_cache
- neon_permute
+ - Added support for FP16 in @ref NEDeconvolutionLayer
+ - Added support for FP16 in @ref CLDeconvolutionLayer
+ - Added support for REDUCE_MIN and REDUCE_MAX in @ref ReductionOperation
- Enable the fusion of batch normalization with convolution and depthwise convolution layer for FP32 in the graph API (OpenCL only)
- Added support for fusing activation function and broadcast addition with the matrix multiplication for FP32 (OpenCL only)
- Re-factored the depthwise convolution layer kernel on NEON for generic cases
@@ -280,6 +293,7 @@ v19.08 Public major release
- The @ref NEDepthwiseConvolutionLayer3x3 will be replaced by @ref NEDepthwiseConvolutionLayerOptimized to accommodate for future optimizations.
- Removed inner_border_right and inner_border_top parameters from @ref CLDeconvolutionLayer interface
- Removed inner_border_right and inner_border_top parameters from @ref NEDeconvolutionLayer interface
+ - Optimized the NEON assembly kernel for GEMMLowp. The new implementation fuses the output stage and quantization with the matrix multiplication kernel
v19.05 Public major release
- Various bug fixes.