From 91f95c715bff84094fc18bad6a8f938291b9b0f5 Mon Sep 17 00:00:00 2001 From: Joseph Redmon <pjreddie@gmail.com> Date: Mon, 24 Oct 2016 20:32:49 +0000 Subject: [PATCH] tree things, tree stuff --- src/blas.h | 18 ++++++++++++++++++ 1 files changed, 18 insertions(+), 0 deletions(-) diff --git a/src/blas.h b/src/blas.h index 030ef66..daacf9a 100644 --- a/src/blas.h +++ b/src/blas.h @@ -1,5 +1,6 @@ #ifndef BLAS_H #define BLAS_H +void reorg(float *x, int size, int layers, int batch, int forward); void pm(int M, int N, float *A); float *random_matrix(int rows, int cols); void time_random_matrix(int TA, int TB, int m, int k, int n); @@ -7,6 +8,7 @@ void test_blas(); void const_cpu(int N, float ALPHA, float *X, int INCX); +void constrain_ongpu(int N, float ALPHA, float * X, int INCX); void pow_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY); void mul_cpu(int N, float *X, int INCX, float *Y, int INCY); @@ -30,13 +32,19 @@ void smooth_l1_cpu(int n, float *pred, float *truth, float *delta, float *error); void l2_cpu(int n, float *pred, float *truth, float *delta, float *error); +void weighted_sum_cpu(float *a, float *b, float *s, int num, float *c); + +void softmax(float *input, int n, float temp, float *output); #ifdef GPU +#include "cuda.h" + void axpy_ongpu(int N, float ALPHA, float * X, int INCX, float * Y, int INCY); void axpy_ongpu_offset(int N, float ALPHA, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY); void copy_ongpu(int N, float * X, int INCX, float * Y, int INCY); void copy_ongpu_offset(int N, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY); void scal_ongpu(int N, float ALPHA, float * X, int INCX); +void supp_ongpu(int N, float ALPHA, float * X, int INCX); void mask_ongpu(int N, float * X, float mask_num, float * mask); void const_ongpu(int N, float ALPHA, float *X, int INCX); void pow_ongpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY); @@ -58,8 +66,18 @@ void scale_bias_gpu(float *output, float *biases, int batch, int n, int size); void backward_scale_gpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates); void scale_bias_gpu(float *output, float *biases, int batch, int n, int size); +void add_bias_gpu(float *output, float *biases, int batch, int n, int size); +void backward_bias_gpu(float *bias_updates, float *delta, int batch, int n, int size); void smooth_l1_gpu(int n, float *pred, float *truth, float *delta, float *error); void l2_gpu(int n, float *pred, float *truth, float *delta, float *error); +void weighted_delta_gpu(float *a, float *b, float *s, float *da, float *db, float *ds, int num, float *dc); +void weighted_sum_gpu(float *a, float *b, float *s, int num, float *c); +void mult_add_into_gpu(int num, float *a, float *b, float *c); + +void reorg_ongpu(float *x, int w, int h, int c, int batch, int stride, int forward, float *out); + +void softmax_gpu(float *input, int n, int offset, int groups, float temp, float *output); + #endif #endif -- Gitblit v1.10.0