diff --git a/impl/sort/topk/topk_common_impl.h b/impl/sort/topk/topk_common_impl.h
index 01d428bde69a0a5591c2e3e797696074b40a0f83..b29b0870bcbaab897cf9cdd0f1bc63edff1f1653 100644
--- a/impl/sort/topk/topk_common_impl.h
+++ b/impl/sort/topk/topk_common_impl.h
@@ -23,6 +23,7 @@
 #include "kernel_pop_stack_buffer.h"
 #include "kernel_tiling/kernel_tiling.h"
 #include "topk_common_utils.h"
+#include "lib/index/arithprogression.h"
 
 #if __CCE_AICORE__ == 220
 #include "topk_v220_impl.h"
diff --git a/lib/activation/softmaxflash.h b/lib/activation/softmaxflash.h
index 9480e9c20e3ba341d702693696e2fca8b71a726f..4a5c6434df88ba9e1d9767d698381512a6789e65 100644
--- a/lib/activation/softmaxflash.h
+++ b/lib/activation/softmaxflash.h
@@ -49,6 +49,7 @@ namespace AscendC {
  *                           you can set true to improve performance
  */
 template <typename T, bool isReuseSource = false, bool isBasicBlock = false>
+[[deprecated(__FILE__ " is deprecated, please use softmaxflashv2.h instead!")]]
 __aicore__ inline void SoftmaxFlash(const LocalTensor<T> &dstTensor, const LocalTensor<T> &sumTensor,
     const LocalTensor<T> &maxTensor, const LocalTensor<T> &srcTensor, const LocalTensor<T> &expMaxTensor,
     const LocalTensor<T> &inSumTensor, const LocalTensor<T> &inMaxTensor, const SoftMaxTiling &tiling,
@@ -87,6 +88,7 @@ __aicore__ inline void SoftmaxFlash(const LocalTensor<T> &dstTensor, const Local
  *                           you can set true to improve performance
  */
 template <typename T, bool isReuseSource = false, bool isBasicBlock = false>
+[[deprecated(__FILE__ " is deprecated, please use softmaxflashv2.h instead!")]]
 __aicore__ inline void SoftmaxFlash(const LocalTensor<half>& dstTensor, const LocalTensor<float>& sumTensor,
     const LocalTensor<float>& maxTensor, const LocalTensor<half>& srcTensor, const LocalTensor<half>& expMaxTensor,
     const LocalTensor<float>& inSumTensor, const LocalTensor<float>& inMaxTensor, const SoftMaxTiling& tiling,
@@ -128,6 +130,7 @@ __aicore__ inline void SoftmaxFlash(const LocalTensor<half>& dstTensor, const Lo
  *                           you can set true to improve performance
  */
 template <typename T, bool isReuseSource = false, bool isBasicBlock = false>
+[[deprecated(__FILE__ " is deprecated, please use softmaxflashv2.h instead!")]]
 __aicore__ inline void SoftmaxFlash(const LocalTensor<T>& dstTensor, const LocalTensor<T>& sumTensor,
     const LocalTensor<T>& maxTensor, const LocalTensor<T>& srcTensor, const LocalTensor<T>& expMaxTensor,
     const LocalTensor<T>& inSumTensor, const LocalTensor<T>& inMaxTensor, const LocalTensor<uint8_t>& sharedTmpBuffer,
@@ -168,6 +171,7 @@ __aicore__ inline void SoftmaxFlash(const LocalTensor<T>& dstTensor, const Local
  *                           you can set true to improve performance
  */
 template <typename T, bool isReuseSource = false, bool isBasicBlock = false>
+[[deprecated(__FILE__ " is deprecated, please use softmaxflashv2.h instead!")]]
 __aicore__ inline void SoftmaxFlash(const LocalTensor<half>& dstTensor, const LocalTensor<float>& sumTensor,
     const LocalTensor<float>& maxTensor, const LocalTensor<half>& srcTensor, const LocalTensor<half>& expMaxTensor,
     const LocalTensor<float>& inSumTensor, const LocalTensor<float>& inMaxTensor,