diff --git a/tt_llk_blackhole/common/inc/cunpack_common.h b/tt_llk_blackhole/common/inc/cunpack_common.h
index 5e859574..ee18f246 100644
--- a/tt_llk_blackhole/common/inc/cunpack_common.h
+++ b/tt_llk_blackhole/common/inc/cunpack_common.h
@@ -192,7 +192,7 @@ namespace ckernel::unpacker
       cfg_reg_rmw_tensix<ALU_FORMAT_SPEC_REG0_SrcA_ADDR32, 0, ALU_ACC_CTRL_INT8_math_enabled_MASK>(alu_payload.val);
    }
 
-   template<bool row_pool=false, bool is_fp32_dest_acc_en = false, bool fpu_srnd_en = false, bool pack_srnd_en = false>
+   template<bool row_pool=false, bool is_fp32_dest_acc_en = false, bool fpu_srnd_en = false, bool pack_srnd_en = false, bool disable_src_zero_flag = false>
    inline void configure_unpack_AB(
      const uint unpA_src_format,
      const uint unpB_src_format,
@@ -272,6 +272,9 @@ namespace ckernel::unpacker
       cfg_reg_rmw_tensix<ALU_FORMAT_SPEC_REG0_SrcA_ADDR32, 0, alu_mask>(alu_payload.val);
 
       uint32_t src_zeroflags_disable = ((uint)unpA_dst_format == (uint)DataFormat::UInt16) || ((uint)unpB_dst_format == (uint)DataFormat::UInt16);
+      if constexpr (disable_src_zero_flag) {
+         src_zeroflags_disable = true;
+      }
       cfg_reg_rmw_tensix<ALU_ACC_CTRL_Zero_Flag_disabled_src_RMW>(src_zeroflags_disable);
 
       //Set FP8 E4M3 mode, bit is accessible by unpacker/packer
diff --git a/tt_llk_blackhole/llk_lib/llk_unpack_A.h b/tt_llk_blackhole/llk_lib/llk_unpack_A.h
index bdb2eb86..b357553d 100644
--- a/tt_llk_blackhole/llk_lib/llk_unpack_A.h
+++ b/tt_llk_blackhole/llk_lib/llk_unpack_A.h
@@ -140,13 +140,13 @@ inline void _llk_unpack_A_mop_config_(const bool transpose_of_faces, const std::
     }
 }
 
-template <bool is_fp32_dest_acc_en = false, StochRndType stoch_rnd_mode = StochRndType::None>
+template <bool is_fp32_dest_acc_en = false, StochRndType stoch_rnd_mode = StochRndType::None, bool disable_src_zero_flag = false>
 inline void _llk_unpack_A_hw_configure_(const std::uint32_t unpack_src_format, const std::uint32_t unpack_dst_format, const std::uint32_t face_r_dim = FACE_R_DIM,  const std::uint32_t within_face_16x16_transpose = 0, const std::uint32_t num_faces = 4) {
     constexpr bool is_row_pool = false;
     constexpr bool stoch_rnd_en = (stoch_rnd_mode == StochRndType::All);
     constexpr bool fpu_srnd_en = stoch_rnd_en || (stoch_rnd_mode == StochRndType::Fpu);
     constexpr bool pack_srnd_en = stoch_rnd_en ||(stoch_rnd_mode == StochRndType::Pack);
-    configure_unpack_AB<is_row_pool, is_fp32_dest_acc_en, fpu_srnd_en, pack_srnd_en>(
+    configure_unpack_AB<is_row_pool, is_fp32_dest_acc_en, fpu_srnd_en, pack_srnd_en, disable_src_zero_flag>(
         unpack_src_format,
         unpack_src_format,
         unpack_dst_format,
diff --git a/tt_llk_wormhole_b0/common/inc/cunpack_common.h b/tt_llk_wormhole_b0/common/inc/cunpack_common.h
index bc70e419..3d44a701 100644
--- a/tt_llk_wormhole_b0/common/inc/cunpack_common.h
+++ b/tt_llk_wormhole_b0/common/inc/cunpack_common.h
@@ -192,7 +192,7 @@ namespace ckernel::unpacker
       cfg_reg_rmw_tensix<ALU_FORMAT_SPEC_REG0_SrcA_ADDR32, 0, ALU_ACC_CTRL_INT8_math_enabled_MASK>(alu_payload.val);
    }
 
-   template<bool row_pool=false, bool is_fp32_dest_acc_en = false, bool fpu_srnd_en = false, bool pack_srnd_en = false>
+   template<bool row_pool=false, bool is_fp32_dest_acc_en = false, bool fpu_srnd_en = false, bool pack_srnd_en = false, bool disable_src_zero_flag = false>
    inline void configure_unpack_AB(
      const uint unpA_src_format,
      const uint unpB_src_format,
@@ -267,6 +267,9 @@ namespace ckernel::unpacker
       cfg_reg_rmw_tensix<ALU_FORMAT_SPEC_REG0_SrcA_ADDR32, 0, alu_mask>(alu_payload.val);
 
       uint32_t src_zeroflags_disable = ((uint)unpA_dst_format == (uint)DataFormat::UInt16) || ((uint)unpB_dst_format == (uint)DataFormat::UInt16);
+      if constexpr (disable_src_zero_flag) {
+         src_zeroflags_disable = true;
+      }
       cfg_reg_rmw_tensix<ALU_ACC_CTRL_Zero_Flag_disabled_src_RMW>(src_zeroflags_disable);
 
       t6_mutex_release(mutex::REG_RMW);
diff --git a/tt_llk_wormhole_b0/llk_lib/llk_unpack_A.h b/tt_llk_wormhole_b0/llk_lib/llk_unpack_A.h
index 3ecbc43f..3ff0352a 100644
--- a/tt_llk_wormhole_b0/llk_lib/llk_unpack_A.h
+++ b/tt_llk_wormhole_b0/llk_lib/llk_unpack_A.h
@@ -141,13 +141,13 @@ inline void _llk_unpack_A_mop_config_(const bool transpose_of_faces, const std::
     }
 }
 
-template <bool is_fp32_dest_acc_en = false, StochRndType stoch_rnd_mode = StochRndType::None>
+template <bool is_fp32_dest_acc_en = false, StochRndType stoch_rnd_mode = StochRndType::None, bool disable_src_zero_flag = false>
 inline void _llk_unpack_A_hw_configure_(const std::uint32_t unpack_src_format, const std::uint32_t unpack_dst_format, const std::uint32_t face_r_dim = FACE_R_DIM,  const std::uint32_t within_face_16x16_transpose = 0, const std::uint32_t num_faces = 4) {
     constexpr bool is_row_pool = false;
     constexpr bool stoch_rnd_en = (stoch_rnd_mode == StochRndType::All);
     constexpr bool fpu_srnd_en = stoch_rnd_en || (stoch_rnd_mode == StochRndType::Fpu);
     constexpr bool pack_srnd_en = stoch_rnd_en ||(stoch_rnd_mode == StochRndType::Pack);
-    configure_unpack_AB<is_row_pool, is_fp32_dest_acc_en, fpu_srnd_en, pack_srnd_en>(
+    configure_unpack_AB<is_row_pool, is_fp32_dest_acc_en, fpu_srnd_en, pack_srnd_en, disable_src_zero_flag>(
         unpack_src_format,
         unpack_src_format,
         unpack_dst_format,