From 68213b835b9f15cb449ad2037a8b51c17a3de07b Mon Sep 17 00:00:00 2001 From: Joseph Redmon <pjreddie@gmail.com> Date: Mon, 14 Mar 2016 22:10:14 +0000 Subject: [PATCH] Makefile --- src/blas.h | 44 +++++++++++++++++++++++++++++++++++++++++++- 1 files changed, 43 insertions(+), 1 deletions(-) diff --git a/src/blas.h b/src/blas.h index 1657fc5..030ef66 100644 --- a/src/blas.h +++ b/src/blas.h @@ -6,11 +6,30 @@ void test_blas(); +void const_cpu(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); + void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY); void copy_cpu(int N, float *X, int INCX, float *Y, int INCY); void scal_cpu(int N, float ALPHA, float *X, int INCX); +void fill_cpu(int N, float ALPHA, float * X, int INCX); float dot_cpu(int N, float *X, int INCX, float *Y, int INCY); void test_gpu_blas(); +void shortcut_cpu(int batch, int w1, int h1, int c1, float *add, int w2, int h2, int c2, float *out); + +void mean_cpu(float *x, int batch, int filters, int spatial, float *mean); +void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance); +void normalize_cpu(float *x, float *mean, float *variance, int batch, int filters, int spatial); + +void scale_bias(float *output, float *scales, int batch, int n, int size); +void backward_scale_cpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates); +void mean_delta_cpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta); +void variance_delta_cpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta); +void normalize_delta_cpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta); + +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); #ifdef GPU void axpy_ongpu(int N, float ALPHA, float * X, int INCX, float * Y, int INCY); @@ -18,6 +37,29 @@ 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 mask_ongpu(int N, float * X, float * mask); +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); +void mul_ongpu(int N, float *X, int INCX, float *Y, int INCY); +void fill_ongpu(int N, float ALPHA, float * X, int INCX); + +void mean_gpu(float *x, int batch, int filters, int spatial, float *mean); +void variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *variance); +void normalize_gpu(float *x, float *mean, float *variance, int batch, int filters, int spatial); + +void normalize_delta_gpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta); + +void fast_mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta); +void fast_variance_delta_gpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta); + +void fast_variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *variance); +void fast_mean_gpu(float *x, int batch, int filters, int spatial, float *mean); +void shortcut_gpu(int batch, int w1, int h1, int c1, float *add, int w2, int h2, int c2, float *out); +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 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); #endif #endif -- Gitblit v1.10.0