From a3ec2dc3bb768e64a32324df9248b226ff96137d Mon Sep 17 00:00:00 2001 From: Bartlomiej Wroblewski Date: Thu, 19 Oct 2023 16:53:18 +0200 Subject: [PATCH] Change 1d,2d,... to 1D,2D,... (#997) [ROCm/composable_kernel commit: 0abc0f87db861cf25395ce9540ecb8e7f4821e4f] --- CHANGELOG.md | 2 +- example/12_reduce/README.md | 4 ++-- example/30_grouped_conv_fwd_multiple_d/README.md | 2 +- profiler/README.md | 8 ++++---- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index f88df081da..3e46a4ab4b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -17,7 +17,7 @@ None - Support for 3D grouped convolution on RDNA 3 GPUs (#935, #950, #985) - Grouped convolution support for small K and C (#822 #879 #897) - Support for NHWGC (2D and 3D) grouped convolution backward weight (#769 #804) -- Support for bf16/f32/f16 and NHWGC (2D and 3d) grouped convolution backward data (#757 #799) +- Support for bf16/f32/f16 and NHWGC (2D and 3D) grouped convolution backward data (#757 #799) - Support for Batched Gemm DL (#732) ### Changes diff --git a/example/12_reduce/README.md b/example/12_reduce/README.md index 76d28527bb..bcffa684c8 100644 --- a/example/12_reduce/README.md +++ b/example/12_reduce/README.md @@ -2,7 +2,7 @@ ## Run ```example_reduce_blockwise``` ```bash -# -D : input 3d/4d/5d tensor lengths +# -D : input 3D/4D/5D tensor lengths # -R : reduce dimension ids # -v : verification (0=no, 1=yes) #arg1: data type (0: fp16, 1: fp32, 3: int8, 5: bp16, 6: fp64, 7: int4) @@ -22,7 +22,7 @@ Perf: 0.238063 ms, 264.285 GB/s, DeviceReduceBlockWise<256,M_C4_S1,K_C64_S1,InSr ## Run ```example_reduce_multiblock_atomic_add``` ```bash -# -D : input 3d/4d/5d tensor lengths +# -D : input 3D/4D/5D tensor lengths # -R : reduce dimension ids # -v : verification (0=no, 1=yes) #arg1: data type (0: fp32, 1: fp64) diff --git a/example/30_grouped_conv_fwd_multiple_d/README.md b/example/30_grouped_conv_fwd_multiple_d/README.md index 739a0425a8..4718795c57 100644 --- a/example/30_grouped_conv_fwd_multiple_d/README.md +++ b/example/30_grouped_conv_fwd_multiple_d/README.md @@ -4,7 +4,7 @@ arg1: verification (0=no, 1=yes) arg2: initialization (0=no init, 1=integer value, 2=decimal value) arg3: time kernel (0=no, 1=yes) Following arguments (depending on number of spatial dims): - Number of spatial dimensions (1=Conv1d, 2=Conv2d, 3=Conv3d) + Number of spatial dimensions (1=Conv1D, 2=Conv2D, 3=Conv3D) G, N, K, C, , (ie Y, X for 2D) , (ie Hi, Wi for 2D) diff --git a/profiler/README.md b/profiler/README.md index a2d370b210..98eae3a763 100644 --- a/profiler/README.md +++ b/profiler/README.md @@ -22,7 +22,7 @@ c_m_n: dim 2, lengths {3840, 4096}, strides {4096, 1} Best Perf: 1.1933 ms, 107.977 TFlops, 79.0848 GB/s ``` -## Profile 2d forward convolution kernels +## Profile 2D forward convolution kernels ```bash #arg1: tensor operation (conv=Convolution) #arg2: data type (0=fp32, 1=fp16) @@ -115,7 +115,7 @@ Best Perf: 58.0306 ms, 37.8942 TFlops, 27.7545 GB/s # arg6: print tensor value (0: no; 1: yes) # arg7: time kernel (0: no, 1: yes) # Following arguments (depending on number of spatial dims): -# Number of spatial dimensions (1=Conv1d, 2=Conv2d, 3=Conv3d) +# Number of spatial dimensions (1=Conv1D, 2=Conv2D, 3=Conv3D) # G, N, K, C, # , (ie Y, X for 2D) # , (ie Hi, Wi for 2D) @@ -158,7 +158,7 @@ GB/s: 127.947 # arg6: print tensor value (0: no; 1: yes) # arg7: time kernel (0: no, 1: yes) # Following arguments (depending on number of spatial dims): -# Number of spatial dimensions (1=Conv1d, 2=Conv2d, 3=Conv3d) +# Number of spatial dimensions (1=Conv1D, 2=Conv2D, 3=Conv3D) # G, N, K, C, # , (ie Y, X for 2D) # , (ie Hi, Wi for 2D) @@ -201,7 +201,7 @@ Note: This kernel use atomic add, this will cause output buffer to be accumulate # arg7: time kernel (0: no, 1: yes) # arg8: operation type (0: ImageToColumn, 1: ColumnToImage) # Following arguments (depending on number of spatial dims): -# Number of spatial dimensions (1=Conv1d, 2=Conv2d, 3=Conv3d) +# Number of spatial dimensions (1=Conv1D, 2=Conv2D, 3=Conv3D) # G, N, K, C, # , (ie Y, X for 2D) # , (ie Hi, Wi for 2D)