From 168af40fe9a3cc81c6ee16b3e81f154780c36bdb Mon Sep 17 00:00:00 2001
From: Scheaven <xuepengqiang>
Date: 星期四, 03 六月 2021 15:03:27 +0800
Subject: [PATCH] up new v4
---
lib/detecter_tools/darknet/cpu_gemm.c | 192 ++++++++++++++++++++++++------------------------
1 files changed, 96 insertions(+), 96 deletions(-)
diff --git a/lib/detecter_tools/darknet/cpu_gemm.c b/lib/detecter_tools/darknet/cpu_gemm.c
index 1919907..ca1a8e4 100644
--- a/lib/detecter_tools/darknet/cpu_gemm.c
+++ b/lib/detecter_tools/darknet/cpu_gemm.c
@@ -1,96 +1,96 @@
-//#include "mini_blas.h"
-#ifdef __cplusplus
-#define PUT_IN_REGISTER
-#else
-#define PUT_IN_REGISTER register
-#endif
-
-void cpu_gemm_nn(int TA, int TB, int M, int N, int K, float ALPHA,
- float *A, int lda,
- float *B, int ldb,
- float BETA,
- float *C, int ldc)
-{
- int i,j,k;
- for(i = 0; i < M; ++i){
- for(k = 0; k < K; ++k){
- PUT_IN_REGISTER float A_PART = ALPHA * A[i * lda + k];
- for(j = 0; j < N; ++j){
- C[i*ldc+j] += A_PART*B[k*ldb+j];
- }
- }
- }
-}
-
-void cpu_gemm_nt(int TA, int TB, int M, int N, int K, float ALPHA,
- float *A, int lda,
- float *B, int ldb,
- float BETA,
- float *C, int ldc)
-{
- int i,j,k;
- for(i = 0; i < M; ++i){
- for(j = 0; j < N; ++j){
- PUT_IN_REGISTER float sum = 0;
- for(k = 0; k < K; ++k){
- sum += ALPHA*A[i*lda+k]*B[k+j*ldb];
- }
- C[i*ldc+j] += sum;
- }
- }
-}
-
-void cpu_gemm_tn(int TA, int TB, int M, int N, int K, float ALPHA,
- float *A, int lda,
- float *B, int ldb,
- float BETA,
- float *C, int ldc)
-{
- int i,j,k;
- for(i = 0; i < M; ++i){
- for(k = 0; k < K; ++k){
- PUT_IN_REGISTER float A_PART = ALPHA * A[k * lda + i];
- for(j = 0; j < N; ++j){
- C[i*ldc+j] += A_PART*B[k*ldb+j];
- }
- }
- }
-}
-void cpu_gemm_tt(int TA, int TB, int M, int N, int K, float ALPHA,
- float *A, int lda,
- float *B, int ldb,
- float BETA,
- float *C, int ldc)
-{
- int i,j,k;
- for(i = 0; i < M; ++i){
- for(j = 0; j < N; ++j){
- for(k = 0; k < K; ++k){
- C[i*ldc+j] += ALPHA*A[i+k*lda]*B[k+j*ldb];
- }
- }
- }
-}
-
-
-void cpu_gemm(int TA, int TB, int M, int N, int K, float ALPHA,
- float *A, int lda,
- float *B, int ldb,
- float BETA,
- float *C, int ldc)
-{
- int i, j;
- for(i = 0; i < M; ++i){
- for(j = 0; j < N; ++j){
- C[i*ldc + j] *= BETA;
- }
- }
- if(!TA && !TB)
- cpu_gemm_nn( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
- else if(TA && !TB)
- cpu_gemm_tn( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
- else if(!TA && TB)
- cpu_gemm_nt( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
- else
- cpu_gemm_tt( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
-}
+//#include "mini_blas.h"
+#ifdef __cplusplus
+#define PUT_IN_REGISTER
+#else
+#define PUT_IN_REGISTER register
+#endif
+
+void cpu_gemm_nn(int TA, int TB, int M, int N, int K, float ALPHA,
+ float *A, int lda,
+ float *B, int ldb,
+ float BETA,
+ float *C, int ldc)
+{
+ int i,j,k;
+ for(i = 0; i < M; ++i){
+ for(k = 0; k < K; ++k){
+ PUT_IN_REGISTER float A_PART = ALPHA * A[i * lda + k];
+ for(j = 0; j < N; ++j){
+ C[i*ldc+j] += A_PART*B[k*ldb+j];
+ }
+ }
+ }
+}
+
+void cpu_gemm_nt(int TA, int TB, int M, int N, int K, float ALPHA,
+ float *A, int lda,
+ float *B, int ldb,
+ float BETA,
+ float *C, int ldc)
+{
+ int i,j,k;
+ for(i = 0; i < M; ++i){
+ for(j = 0; j < N; ++j){
+ PUT_IN_REGISTER float sum = 0;
+ for(k = 0; k < K; ++k){
+ sum += ALPHA*A[i*lda+k]*B[k+j*ldb];
+ }
+ C[i*ldc+j] += sum;
+ }
+ }
+}
+
+void cpu_gemm_tn(int TA, int TB, int M, int N, int K, float ALPHA,
+ float *A, int lda,
+ float *B, int ldb,
+ float BETA,
+ float *C, int ldc)
+{
+ int i,j,k;
+ for(i = 0; i < M; ++i){
+ for(k = 0; k < K; ++k){
+ PUT_IN_REGISTER float A_PART = ALPHA * A[k * lda + i];
+ for(j = 0; j < N; ++j){
+ C[i*ldc+j] += A_PART*B[k*ldb+j];
+ }
+ }
+ }
+}
+void cpu_gemm_tt(int TA, int TB, int M, int N, int K, float ALPHA,
+ float *A, int lda,
+ float *B, int ldb,
+ float BETA,
+ float *C, int ldc)
+{
+ int i,j,k;
+ for(i = 0; i < M; ++i){
+ for(j = 0; j < N; ++j){
+ for(k = 0; k < K; ++k){
+ C[i*ldc+j] += ALPHA*A[i+k*lda]*B[k+j*ldb];
+ }
+ }
+ }
+}
+
+
+void cpu_gemm(int TA, int TB, int M, int N, int K, float ALPHA,
+ float *A, int lda,
+ float *B, int ldb,
+ float BETA,
+ float *C, int ldc)
+{
+ int i, j;
+ for(i = 0; i < M; ++i){
+ for(j = 0; j < N; ++j){
+ C[i*ldc + j] *= BETA;
+ }
+ }
+ if(!TA && !TB)
+ cpu_gemm_nn( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
+ else if(TA && !TB)
+ cpu_gemm_tn( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
+ else if(!TA && TB)
+ cpu_gemm_nt( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
+ else
+ cpu_gemm_tt( TA, TB, M, N, K, ALPHA,A,lda, B, ldb,BETA,C,ldc);
+}
--
Gitblit v1.8.0