From d8adaf8ea6a31a380f6bf1fe65e88b661d3bb51e Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 21 Oct 2016 20:16:43 +0000
Subject: [PATCH] tree stuff

---
 src/blas.h |   10 ++++++++++
 1 files changed, 10 insertions(+), 0 deletions(-)

diff --git a/src/blas.h b/src/blas.h
index 47d930c..6b6b8f5 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);
@@ -31,13 +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);
@@ -68,6 +75,9 @@
 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 groups, float temp, float *output, cudaStream_t stream);
 
 #endif
 #endif

--
Gitblit v1.10.0