feat(dnn/fallback): add im2col filterpreprocess function

GitOrigin-RevId: 61c54ad258

dnn/src/fallback/conv_bias/im2col/algos.cpp

@@ -31,35 +31,10 @@ using namespace im2col;
  *  *Through witch can convenient get the needed ptr
  */
 struct Im2colBundelIndex {
-    static constexpr size_t BUNDLE_PADDING_INDEX = 0_z;
-    static constexpr size_t BUNDLE_PACKA_INDEX = 1_z;
     static constexpr size_t BUNDLE_THREAD_INDEX = 2_z;
 };
 
 using Pack_Mode=fallback::MatrixMulImpl::AlgoBase::PackMode;
-
-//! Process one input channel copy padding
-static void copy_padding_kern(WorkspaceBundle& bundle,
-                              const ConvBiasImpl::NCBKernParam& param,
-                              const ConvBiasImpl::NCBKernIndex& ncb_index,
-                              StrategyBase* im2colstrategy, size_t pack_oc_size) {
-    im2colstrategy->copy_padding_kern(bundle, param, ncb_index, pack_oc_size);
-}
-
-//! packA_kern
-static void packA_kern(
-        WorkspaceBundle& bundle,
-        const fallback::ConvBiasImpl::NCBKernParam& param,
-        fallback::MatrixMulImpl::KernSizeParam matmulparam,
-        fallback::MatrixMulImpl::AlgoBase* matmul_algo,
-        const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
-        StrategyBase* im2colstrategy,
-        const fallback::MatrixMulImpl::AlgoBase::MatmulDescription& matmul_desc,
-        size_t pack_oc_size) {
-    im2colstrategy->packA_kern(bundle, param, matmulparam, matmul_algo,
-                               ncb_index, matmul_desc, pack_oc_size);
-}
-
 /*!
  * *\brief Im2colKerns collects all the im2col kerns in it
  */
@@ -124,8 +99,8 @@ public:
 
     WorkspaceBundle get_thread_bundle(
             const fallback::ConvBiasImpl::NCBKernSizeParam& param,
-            fallback::MatrixMulImpl::KernSizeParam im2col_kern_param,
-            MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size,
+            const fallback::MatrixMulImpl::KernSizeParam& im2col_kern_param,
+            const MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size,
             size_t oc_tile_size) {
         size_t IC = param.filter_meta.icpg, FH = param.filter_meta.spatial[0],
                FW = param.filter_meta.spatial[1];
@@ -205,8 +180,8 @@ public:
     }
     WorkspaceBundle get_thread_bundle(
             const fallback::ConvBiasImpl::NCBKernSizeParam& param,
-            fallback::MatrixMulImpl::KernSizeParam im2col_kern_param,
-            MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size,
+            const fallback::MatrixMulImpl::KernSizeParam& im2col_kern_param,
+            const MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size,
             size_t oc_tile_size) {
         size_t IC = param.filter_meta.icpg, FH = param.filter_meta.spatial[0],
                FW = param.filter_meta.spatial[1];
@@ -288,8 +263,8 @@ public:
     }
     WorkspaceBundle get_thread_bundle(
             const fallback::ConvBiasImpl::NCBKernSizeParam& param,
-            fallback::MatrixMulImpl::KernSizeParam im2col_kern_param,
-            MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size,
+            const fallback::MatrixMulImpl::KernSizeParam& im2col_kern_param,
+            const MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size,
             size_t oc_tile_size) {
         size_t IC = param.filter_meta.icpg, FH = param.filter_meta.spatial[0],
                FW = param.filter_meta.spatial[1];
@@ -322,15 +297,16 @@ public:
     }
 };
 
-fallback::MatrixMulImpl::KernSizeParam
-ConvBiasImpl::AlgoIm2col ::get_matmul_kern_param(const NCBKernSizeParam& param,
-                                                 size_t ohw_tile_size,
-                                                 size_t oc_tile_size) const {
+namespace {
+static fallback::MatrixMulImpl::KernSizeParam get_matmul_kern_param(
+        const fallback::ConvBiasImpl::NCBKernSizeParam& param,
+        size_t ohw_tile_size, size_t oc_tile_size) {
     auto format = param::MatrixMul::Format::DEFAULT;
     size_t pack_oc_size = pack_size(param.filter_meta.format);
     if (param.filter_meta.format == param::ConvBias::Format::NCHW44) {
         format = param::MatrixMul::Format::MK4;
-    } else if(param.filter_meta.format == param::ConvBias::Format::NCHW44_DOT){
+    } else if (param.filter_meta.format ==
+               param::ConvBias::Format::NCHW44_DOT) {
         format = param::MatrixMul::Format::MK4_DOT;
     }
     size_t M = oc_tile_size;
@@ -358,10 +334,23 @@ ConvBiasImpl::AlgoIm2col ::get_matmul_kern_param(const NCBKernSizeParam& param,
             format};
 }
 
-void ConvBiasImpl::AlgoIm2col::choice_ohw_oc_block(
-        const NCBKernSizeParam& param, size_t& oc_tile_size,
-        size_t& ohw_tile_size, size_t block_m, size_t block_n,
-        fallback::MatrixMulImpl::AlgoBase::PackMode pack_mode) const {
+static void choice_ohw_oc_block(
+        const fallback::ConvBiasImpl::NCBKernSizeParam& param,
+        size_t& oc_tile_size, size_t& ohw_tile_size, size_t block_m,
+        size_t block_n, const size_t m_ohw_tile_size,
+        fallback::MatrixMulImpl::AlgoBase::PackMode pack_mode) {
+    //! calculate m_oc_tile_size in choice_ohw_oc_block() fucntion,
+    //! when ohw_tile_size < this value ohw_tile_size = ohw
+    static constexpr size_t DEFAULT_OHW_MIN_TILE_SIZE = 32;
+    //! when nr_threads > 1 and round(ohw,nr_threads)>nr_threads,
+    //! oc_tile_size = DEFAULT_OC_TILE_SIZE
+    static constexpr size_t DEFAULT_OC_TILE_SIZE = 512;
+    //! when oc_tile_size > this value m_oc_tile_size =
+    //! DEFAULT_OC_MAX_TILE_SIZE
+    static constexpr size_t DEFAULT_OC_MAX_TILE_SIZE = 1024;
+    //! when oc_tile_size < this value oc_tile_size =
+    //! DEFAULT_OC_MIN_TILE_SIZE the purpose is aligning the calculation
+    static constexpr size_t DEFAULT_OC_MIN_TILE_SIZE = 128;
     size_t nr_threads = param.nr_threads;
     size_t OC = param.filter_meta.ocpg;
     size_t ohw = param.osz[0] * param.osz[1];
@@ -393,8 +382,74 @@ void ConvBiasImpl::AlgoIm2col::choice_ohw_oc_block(
     }
 }
 
-WorkspaceBundle ConvBiasImpl::AlgoIm2col::get_bundle(
-        const NCBKernSizeParam& param) const {
+static size_t packA_group_size(
+        const MatrixMulImpl::AlgoBase* matmul_algo,
+        const fallback::MatrixMulImpl::KernSizeParam& matmul_param,
+        const fallback::MatrixMulImpl::AlgoBase::MatmulDescription& matmul_desc,
+        size_t packa_parallel_times) {
+    if (matmul_desc.packmode ==
+        fallback::MatrixMulImpl::AlgoBase::PackMode::DEFAULT) {
+        return matmul_algo->get_bundle(matmul_param).get_size(0);
+    } else if (matmul_desc.packmode ==
+               fallback::MatrixMulImpl::AlgoBase::PackMode::ONLY_PACKA) {
+        return packa_parallel_times *
+               matmul_algo->get_bundle(matmul_param).get_size(0);
+    }
+    megdnn_assert(matmul_desc.packmode ==
+                  fallback::MatrixMulImpl::AlgoBase::PackMode::NO_PACK);
+    //! nopack mode return 0;
+    return 0;
+}
+
+static WorkspaceBundle get_thread_bundle(
+        const fallback::ConvBiasImpl::NCBKernSizeParam& param,
+        const MatrixMulImpl::AlgoBase* matmul_algo,
+        const fallback::MatrixMulImpl::KernSizeParam& matmul_param,
+        const fallback::MatrixMulImpl::AlgoBase::MatmulDescription& matmul_desc,
+        size_t oc_tile_size, size_t ohw_tile_size) {
+    if (matmul_desc.packmode == Pack_Mode::DEFAULT) {
+        MIDOUT_BEGIN(
+                megdnn_fallback_im2col,
+                midout_iv("ConvBiasImpl::AlgoIm2col::get_bundle_dft"_hash)) {
+            Im2colKerns<Pack_Mode::DEFAULT> defaultkern;
+            return defaultkern.get_thread_bundle(param, matmul_param,
+                                                 matmul_algo, ohw_tile_size,
+                                                 oc_tile_size);
+        }
+        MIDOUT_END();
+    } else if (matmul_desc.packmode ==
+               fallback::MatrixMulImpl::AlgoBase::PackMode::ONLY_PACKA) {
+        MIDOUT_BEGIN(
+                megdnn_fallback_im2col,
+                midout_iv(
+                        "ConvBiasImpl::AlgoIm2col::get_bundle_onlypacka"_hash)) {
+            Im2colKerns<Pack_Mode::ONLY_PACKA> onlypackakern;
+            return onlypackakern.get_thread_bundle(param, matmul_param,
+                                                   matmul_algo, ohw_tile_size,
+                                                   oc_tile_size);
+        }
+        MIDOUT_END();
+    } else {
+        megdnn_assert(matmul_desc.packmode ==
+                      fallback::MatrixMulImpl::AlgoBase::PackMode::NO_PACK);
+        MIDOUT_BEGIN(
+                megdnn_fallback_im2col,
+                midout_iv(
+                        "ConvBiasImpl::AlgoIm2col::get_thread_bundle_nopack"_hash)) {
+            Im2colKerns<Pack_Mode::NO_PACK> nopackkern;
+            return nopackkern.get_thread_bundle(param, matmul_param,
+                                                matmul_algo, ohw_tile_size,
+                                                oc_tile_size);
+        }
+        MIDOUT_END();
+    }
+    return {nullptr, {}};
+}
+
+static WorkspaceBundle get_bundle(
+        const fallback::ConvBiasImpl::NCBKernSizeParam& param,
+        MatrixMulImpl::AlgoBase* matmul_algo, size_t oc_tile_size,
+        size_t ohw_tile_size) {
     UNPACK_CONV_F32_NCB_KERN_SIZES(param);
     MEGDNN_MARK_USED_VAR(OC);
     MEGDNN_MARK_USED_VAR(OH);
@@ -410,23 +465,20 @@ WorkspaceBundle ConvBiasImpl::AlgoIm2col::get_bundle(
     size_t padding = 0, packa_size = 0, packa_group_size = 0;
     size_t nr_threads = param.nr_threads;
     size_t GROUP = param.filter_meta.group;
-    fallback::MatrixMulImpl::AlgoBase::MatmulDescription mdesc =
-            m_matmul_algo->matmul_description();
-    bool need_pack = mdesc.packmode == Pack_Mode::DEFAULT;
-    bool only_packA = mdesc.packmode == Pack_Mode::ONLY_PACKA;
-    size_t oc_tile_size = 0, ohw_tile_size = 0;
-    choice_ohw_oc_block(param, oc_tile_size, ohw_tile_size,
-                        mdesc.innerblocksize.m, mdesc.innerblocksize.n,
-                        mdesc.packmode);
-    if (need_pack || only_packA) {
-        auto im2col_kern_param = get_matmul_kern_param(
-                param, ohw_tile_size, only_packA ? oc_tile_size : OC);
-        size_t oc_parallel_times = div_ceil<size_t>(OC, oc_tile_size);
-        WorkspaceBundle wb = m_matmul_algo->get_bundle(im2col_kern_param);
-        packa_group_size = only_packA ? oc_parallel_times * wb.get_size(0)
-                                      : wb.get_size(0);
-    } else {  //! not support pack,not need pack
+    fallback::MatrixMulImpl::AlgoBase::MatmulDescription matmul_desc =
+            matmul_algo->matmul_description();
+    bool default_pack = matmul_desc.packmode == Pack_Mode::DEFAULT;
+
+    //! packmode is default should use oc
+    //! packmode is onlypackA should use oc_tile_size
+    auto im2col_kern_param = get_matmul_kern_param(
+            param, ohw_tile_size, default_pack ? OC : oc_tile_size);
+    if (is_enable_filter_preprocess(param)) {
         packa_group_size = 0;
+    } else {
+        size_t oc_parallel_times = div_ceil<size_t>(OC, oc_tile_size);
+        packa_group_size = packA_group_size(matmul_algo, im2col_kern_param,
+                                            matmul_desc, oc_parallel_times);
     }
 
     if (no_need_pading) {
@@ -437,50 +489,27 @@ WorkspaceBundle ConvBiasImpl::AlgoIm2col::get_bundle(
     }
 
     packa_size = GROUP * packa_group_size;  //! for packA  size = GROUP * a_size
-    WorkspaceBundle ws = {nullptr, {}};
-    auto im2col_kern_param =
-            get_matmul_kern_param(param, ohw_tile_size, oc_tile_size);
-
-    if (m_matmul_algo->packmode() == Pack_Mode::DEFAULT) {
-        MIDOUT_BEGIN(
-                megdnn_fallback_im2col,
-                midout_iv("ConvBiasImpl::AlgoIm2col::get_bundle_dft"_hash)) {
-            Im2colKerns<Pack_Mode::DEFAULT> defaultkern;
-            ws = defaultkern.get_thread_bundle(param, im2col_kern_param,
-                                               m_matmul_algo, ohw_tile_size,
-                                               oc_tile_size);
-        }
-        MIDOUT_END();
-    } else if (m_matmul_algo->packmode() == Pack_Mode::ONLY_PACKA) {
-        MIDOUT_BEGIN(
-                megdnn_fallback_im2col,
-                midout_iv("ConvBiasImpl::AlgoIm2col::get_bundle_packa"_hash)) {
-            Im2colKerns<Pack_Mode::ONLY_PACKA> onlypackakern;
-            ws = onlypackakern.get_thread_bundle(param, im2col_kern_param,
-                                                 m_matmul_algo, ohw_tile_size,
-                                                 oc_tile_size);
-        }
-        MIDOUT_END();
-    } else {
-        MIDOUT_BEGIN(
-                megdnn_fallback_im2col,
-                midout_iv("ConvBiasImpl::AlgoIm2col::get_bundle_other"_hash)) {
-            Im2colKerns<Pack_Mode::NO_PACK> nopackkern;
-            ws = nopackkern.get_thread_bundle(param, im2col_kern_param,
-                                              m_matmul_algo, ohw_tile_size,
-                                              oc_tile_size);
-        }
-        MIDOUT_END();
-    }
 
+    WorkspaceBundle ws =
+            get_thread_bundle(param, matmul_algo, im2col_kern_param,
+                              matmul_desc, oc_tile_size, ohw_tile_size);
     return {nullptr,
             {padding, packa_size, ws.total_size_in_bytes() * nr_threads}};
 }
 
+}  // namespace
+
 size_t ConvBiasImpl::AlgoIm2col::get_workspace(
         const NCBKernSizeParam& p) const {
     MIDOUT_BEGIN(megdnn_fallback_im2col, 0, 0) {
-        return get_bundle(p).total_size_in_bytes();
+        fallback::MatrixMulImpl::AlgoBase::MatmulDescription matmul_desc =
+                m_matmul_algo->matmul_description();
+        size_t oc_tile_size = 0, ohw_tile_size = 0;
+        choice_ohw_oc_block(p, oc_tile_size, ohw_tile_size,
+                            matmul_desc.innerblocksize.m, matmul_desc.innerblocksize.n,
+                            m_ohw_tile_size, matmul_desc.packmode);
+        return get_bundle(p, m_matmul_algo, oc_tile_size, ohw_tile_size)
+                .total_size_in_bytes();
     }
     MIDOUT_END();
     return 0;
@@ -499,22 +528,21 @@ SmallVector<ConvBiasImpl::NCBKern> ConvBiasImpl::AlgoIm2col::dispatch_kerns(
         size_t oc_tile_size = 0, ohw_tile_size = 0;
         size_t ohw = OH * OW;
         size_t GROUP = param.filter_meta.group;
-        WorkspaceBundle bundle = get_bundle(param);
-        WorkspaceBundle bundle_thread = {nullptr, {}};
         bool need_padding = (PH != 0 || PW != 0);
 
-        fallback::MatrixMulImpl::AlgoBase::MatmulDescription mdesc =
+        fallback::MatrixMulImpl::AlgoBase::MatmulDescription matmul_desc =
                 m_matmul_algo->matmul_description();
 
-        Pack_Mode packmode = mdesc.packmode;
-        bool default_pack = packmode == Pack_Mode::DEFAULT;
-        bool no_pack = packmode == Pack_Mode::NO_PACK;
-        bool only_packA = packmode == Pack_Mode::ONLY_PACKA;
-
+        bool default_pack = matmul_desc.packmode == Pack_Mode::DEFAULT;
+        bool no_pack = matmul_desc.packmode == Pack_Mode::NO_PACK;
+        bool only_packA = matmul_desc.packmode == Pack_Mode::ONLY_PACKA;
+        bool enable_filter_preprocess = is_enable_filter_preprocess(param);
         choice_ohw_oc_block(param, oc_tile_size, ohw_tile_size,
-                            mdesc.innerblocksize.m, mdesc.innerblocksize.n,
-                            mdesc.packmode);
+                            matmul_desc.innerblocksize.m,
+                            matmul_desc.innerblocksize.n, m_ohw_tile_size,
+                            matmul_desc.packmode);
 
+        WorkspaceBundle bundle = get_bundle(param,m_matmul_algo,oc_tile_size,ohw_tile_size);
         size_t ohw_parallel_times = div_ceil(ohw, ohw_tile_size);
         size_t oc_parallel_times = div_ceil<size_t>(OC, oc_tile_size);
         size_t packa_parallel_times = 0;
@@ -523,28 +551,16 @@ SmallVector<ConvBiasImpl::NCBKern> ConvBiasImpl::AlgoIm2col::dispatch_kerns(
         if (only_packA) {
             packa_parallel_times = div_ceil<size_t>(OC, oc_tile_size);
         } else if (default_pack) {
-            packa_parallel_times = div_ceil<size_t>(OC, mdesc.innerblocksize.m);
+            packa_parallel_times =
+                    div_ceil<size_t>(OC, matmul_desc.innerblocksize.m);
         }
 
         auto matmul_param = get_matmul_kern_param(
-                param, ohw_tile_size, only_packA ? oc_tile_size : OC);
-        if (mdesc.packmode == Pack_Mode::DEFAULT) {
-            Im2colKerns<Pack_Mode::DEFAULT> defaultkern;
-            bundle_thread = defaultkern.get_thread_bundle(
-                    param, matmul_param, m_matmul_algo, ohw_tile_size,
-                    oc_tile_size);
-        } else if (mdesc.packmode == Pack_Mode::ONLY_PACKA) {
-            Im2colKerns<Pack_Mode::ONLY_PACKA> onlypackakern;
-            bundle_thread = onlypackakern.get_thread_bundle(
-                    param, matmul_param, m_matmul_algo, ohw_tile_size,
-                    oc_tile_size);
-        } else {
-            Im2colKerns<Pack_Mode::NO_PACK> nopackkern;
-            bundle_thread = nopackkern.get_thread_bundle(
-                    param, matmul_param, m_matmul_algo, ohw_tile_size,
-                    oc_tile_size);
-        }
+                param, ohw_tile_size, default_pack ? OC : oc_tile_size);
 
+        WorkspaceBundle bundle_thread =
+                get_thread_bundle(param, m_matmul_algo, matmul_param,
+                                  matmul_desc, oc_tile_size, ohw_tile_size);
         StrategyParam strategyparam;
         strategyparam.ohw = ohw;
         strategyparam.is_dst_8bit =
@@ -557,6 +573,9 @@ SmallVector<ConvBiasImpl::NCBKern> ConvBiasImpl::AlgoIm2col::dispatch_kerns(
                 strategyparam.is_ohw_size_bigger && !strategyparam.is_dst_8bit;
         strategyparam.oc_tile_size = oc_tile_size;
         strategyparam.pack_oc_size = pack_oc_size;
+        strategyparam.enable_filter_preprocess = enable_filter_preprocess;
+        strategyparam.packA_group_size = packA_group_size(
+                m_matmul_algo, matmul_param, matmul_desc, packa_parallel_times);
 
         SmallVector<ConvBiasImpl::NCBKern> ret_kern;
         MIDOUT_BEGIN(
@@ -569,88 +588,126 @@ SmallVector<ConvBiasImpl::NCBKern> ConvBiasImpl::AlgoIm2col::dispatch_kerns(
                                         const NCBKernParam& param,
                                         const NCBKernIndex& ncb_index) mutable {
                 bundle.set(param.workspace_ptr);
-                copy_padding_kern(bundle, param, ncb_index, im2colstrategy,
-                                  pack_oc_size);
+                im2colstrategy->copy_padding_kern(bundle, param, ncb_index,
+                                                  pack_oc_size);
             };
 
             auto kern_packA = [bundle, matmul_algo = m_matmul_algo,
                                matmul_param, im2colstrategy,
-                               pack_oc_size = pack_oc_size, mdesc = mdesc](
+                               strategyparam = strategyparam,
+                               matmul_desc = matmul_desc](
                                       const NCBKernParam& param,
                                       const NCBKernIndex& ncb_index) mutable {
                 bundle.set(param.workspace_ptr);
-                packA_kern(bundle, param, matmul_param, matmul_algo, ncb_index,
-                           im2colstrategy, mdesc, pack_oc_size);
+
+                im2colstrategy->packA_kern(bundle, param, matmul_param,
+                                           matmul_algo, ncb_index, matmul_desc,
+                                           strategyparam);
             };
             if (default_pack) {
-                auto kern_compute_default =
-                        [bundle, bundle_thread, matmul_param,
-                         matmul_algo = m_matmul_algo,
-                         ohw_tile_size = ohw_tile_size,
-                         strategyparam = strategyparam, matmul_desc = mdesc,
-                         im2colstrategy](
-                                const NCBKernParam& param,
-                                const NCBKernIndex& ncb_index) mutable {
-                            bundle.set(param.workspace_ptr);
-                            Im2colKerns<Pack_Mode::DEFAULT>::kerns(
-                                    bundle, bundle_thread, param, matmul_param,
-                                    matmul_algo, matmul_desc, strategyparam,
-                                    ncb_index, ohw_tile_size, im2colstrategy);
-                        };
-                ret_kern.push_back({kern_packA, {GROUP, packa_parallel_times}});
-
-                if (need_padding) {
-                    ret_kern.push_back({kern_padding,
-                                        {param.n, GROUP, IC / pack_oc_size}});
+                MIDOUT_BEGIN(
+                        megdnn_fallback_im2col,
+                        midout_iv(
+                                "ConvBiasImpl::AlgoIm2col::dispatch_kerns_default_pack"_hash)) {
+                    auto kern_compute_default =
+                            [bundle, bundle_thread, matmul_param,
+                             matmul_algo = m_matmul_algo,
+                             ohw_tile_size = ohw_tile_size,
+                             strategyparam = strategyparam,
+                             matmul_desc = matmul_desc, im2colstrategy](
+                                    const NCBKernParam& param,
+                                    const NCBKernIndex& ncb_index) mutable {
+                                bundle.set(param.workspace_ptr);
+                                Im2colKerns<Pack_Mode::DEFAULT>::kerns(
+                                        bundle, bundle_thread, param,
+                                        matmul_param, matmul_algo, matmul_desc,
+                                        strategyparam, ncb_index, ohw_tile_size,
+                                        im2colstrategy);
+                            };
+                    if (!enable_filter_preprocess) {
+                        ret_kern.push_back(
+                                {kern_packA, {GROUP, packa_parallel_times}});
+                    }
+                    if (need_padding) {
+                        ret_kern.push_back(
+                                {kern_padding,
+                                 {param.n, GROUP, IC / pack_oc_size}});
+                    }
+                    ret_kern.push_back({kern_compute_default,
+                                        {N, GROUP, ohw_parallel_times,
+                                         oc_parallel_times}});
+                    return ret_kern;
                 }
-                ret_kern.push_back(
-                        {kern_compute_default,
-                         {N, GROUP, ohw_parallel_times, oc_parallel_times}});
+                MIDOUT_END();
+                return {};
             } else if (only_packA) {
-                auto kern_compute_onlypackA =
-                        [bundle, bundle_thread, matmul_param,
-                         matmul_algo = m_matmul_algo,
-                         strategyparam = strategyparam,
-                         ohw_tile_size = ohw_tile_size, matmul_desc = mdesc,
-                         im2colstrategy](
-                                const NCBKernParam& param,
-                                const NCBKernIndex& ncb_index) mutable {
-                            bundle.set(param.workspace_ptr);
-                            Im2colKerns<Pack_Mode::ONLY_PACKA>::kerns(
-                                    bundle, bundle_thread, param, matmul_param,
-                                    matmul_algo, matmul_desc, strategyparam,
-                                    ncb_index, ohw_tile_size, im2colstrategy);
-                        };
-                ret_kern.push_back({kern_packA, {GROUP, packa_parallel_times}});
-                if (need_padding) {
-                    ret_kern.push_back({kern_padding, {param.n, GROUP, IC}});
+                MIDOUT_BEGIN(
+                        megdnn_fallback_im2col,
+                        midout_iv(
+                                "ConvBiasImpl::AlgoIm2col::dispatch_kerns_onlypacka"_hash)) {
+                    auto kern_compute_onlypackA =
+                            [bundle, bundle_thread, matmul_param,
+                             matmul_algo = m_matmul_algo,
+                             strategyparam = strategyparam,
+                             ohw_tile_size = ohw_tile_size,
+                             matmul_desc = matmul_desc, im2colstrategy](
+                                    const NCBKernParam& param,
+                                    const NCBKernIndex& ncb_index) mutable {
+                                bundle.set(param.workspace_ptr);
+                                Im2colKerns<Pack_Mode::ONLY_PACKA>::kerns(
+                                        bundle, bundle_thread, param,
+                                        matmul_param, matmul_algo, matmul_desc,
+                                        strategyparam, ncb_index, ohw_tile_size,
+                                        im2colstrategy);
+                            };
+                    if (!enable_filter_preprocess) {
+                        ret_kern.push_back(
+                                {kern_packA, {GROUP, packa_parallel_times}});
+                    }
+                    if (need_padding) {
+                        ret_kern.push_back(
+                                {kern_padding, {param.n, GROUP, IC}});
+                    }
+                    ret_kern.push_back({kern_compute_onlypackA,
+                                        {N, GROUP, ohw_parallel_times,
+                                         oc_parallel_times}});
+                    return ret_kern;
                 }
-                ret_kern.push_back(
-                        {kern_compute_onlypackA,
-                         {N, GROUP, ohw_parallel_times, oc_parallel_times}});
+                MIDOUT_END();
+                return {};
             } else if (no_pack) {
-                auto kern_compute_nopack =
-                        [bundle, bundle_thread, matmul_param,
-                         matmul_algo = m_matmul_algo,
-                         strategyparam = strategyparam,
-                         ohw_tile_size = ohw_tile_size, matmul_desc = mdesc,
-                         im2colstrategy](
-                                const NCBKernParam& param,
-                                const NCBKernIndex& ncb_index) mutable {
-                            bundle.set(param.workspace_ptr);
-                            Im2colKerns<Pack_Mode::NO_PACK>::kerns(
-                                    bundle, bundle_thread, param, matmul_param,
-                                    matmul_algo, matmul_desc, strategyparam,
-                                    ncb_index, ohw_tile_size, im2colstrategy);
-                        };
-                if (need_padding) {
-                    ret_kern.push_back({kern_padding, {param.n, GROUP, IC}});
+                MIDOUT_BEGIN(
+                        megdnn_fallback_im2col,
+                        midout_iv(
+                                "ConvBiasImpl::AlgoIm2col::dispatch_kerns_no_pack"_hash)) {
+                    auto kern_compute_nopack =
+                            [bundle, bundle_thread, matmul_param,
+                             matmul_algo = m_matmul_algo,
+                             strategyparam = strategyparam,
+                             ohw_tile_size = ohw_tile_size,
+                             matmul_desc = matmul_desc, im2colstrategy](
+                                    const NCBKernParam& param,
+                                    const NCBKernIndex& ncb_index) mutable {
+                                bundle.set(param.workspace_ptr);
+                                Im2colKerns<Pack_Mode::NO_PACK>::kerns(
+                                        bundle, bundle_thread, param,
+                                        matmul_param, matmul_algo, matmul_desc,
+                                        strategyparam, ncb_index, ohw_tile_size,
+                                        im2colstrategy);
+                            };
+                    if (need_padding) {
+                        ret_kern.push_back(
+                                {kern_padding, {param.n, GROUP, IC}});
+                    }
+                    ret_kern.push_back({kern_compute_nopack,
+                                        {N, GROUP, ohw_parallel_times,
+                                         oc_parallel_times}});
+                    return ret_kern;
                 }
-                ret_kern.push_back(
-                        {kern_compute_nopack,
-                         {N, GROUP, ohw_parallel_times, oc_parallel_times}});
+                MIDOUT_END();
+                return {};
             }
-            return ret_kern;
+            return {};
         }
         MIDOUT_END();
         return {};
@@ -694,12 +751,19 @@ bool ConvBiasImpl::AlgoIm2col::usable(
                 return false;
             }
         }
-        fallback::MatrixMulImpl::AlgoBase::MatmulDescription mdesc =
+        fallback::MatrixMulImpl::AlgoBase::MatmulDescription matmul_desc =
                 m_matmul_algo->matmul_description();
+        //! only matmul's packmode is packa or default support weight preprocess
+        if (is_enable_filter_preprocess(param) &&
+            (matmul_desc.packmode ==
+             fallback::MatrixMulImpl::AlgoBase::PackMode::NO_PACK)) {
+            return false;
+        }
+
         if (format == param::ConvBias::Format::NCHW44 ||
             format == param::ConvBias::Format::NCHW44_DOT) {
             //! current NCHW44 im2col only support DEFAULT mode matmul
-            if (mdesc.packmode != Pack_Mode::DEFAULT) {
+            if (matmul_desc.packmode != Pack_Mode::DEFAULT) {
                 return false;
                 //! nchw44 hybird mode and channel wise is not support
             } else if (param.filter_meta.icpg < 4_z ||
@@ -711,8 +775,9 @@ bool ConvBiasImpl::AlgoIm2col::usable(
 
         size_t oc_tile_size = 0, ohw_tile_size = 0;
         choice_ohw_oc_block(param, oc_tile_size, ohw_tile_size,
-                            mdesc.innerblocksize.m, mdesc.innerblocksize.n,
-                            m_matmul_algo->packmode());
+                            matmul_desc.innerblocksize.m,
+                            matmul_desc.innerblocksize.n, m_ohw_tile_size,
+                            matmul_desc.packmode);
         fallback::MatrixMulImpl::KernSizeParam matmul_param =
                 get_matmul_kern_param(param, ohw_tile_size, oc_tile_size);
         bool matmulusable = m_matmul_algo->usable(matmul_param);
@@ -731,4 +796,104 @@ bool ConvBiasImpl::AlgoIm2col::usable(
     return false;
 }
 
+SmallVector<TensorLayout>
+ConvBiasImpl::AlgoIm2col::deduce_preprocessed_filter_layout(
+        const NCBKernSizeParam& param) const {
+    MIDOUT_BEGIN(
+            megdnn_fallback_im2col,
+            midout_iv(
+                    "ConvBiasImpl::AlgoIm2col::deduce_preprocessed_filter_layout"_hash)) {
+        fallback::MatrixMulImpl::AlgoBase::MatmulDescription matmul_desc =
+                m_matmul_algo->matmul_description();
+
+        //! only support default_pack and only_packa mode
+        if (matmul_desc.packmode == Pack_Mode::NO_PACK) {
+            return {};
+        }
+
+        size_t GROUP = param.filter_meta.group;
+        bool default_pack = matmul_desc.packmode == Pack_Mode::DEFAULT;
+
+        size_t OC = param.filter_meta.ocpg;
+        SmallVector<TensorLayout> preprocessed_layouts;
+        size_t oc_tile_size = 0, ohw_tile_size = 0;
+        choice_ohw_oc_block(param, oc_tile_size, ohw_tile_size,
+                            matmul_desc.innerblocksize.m,
+                            matmul_desc.innerblocksize.n, m_ohw_tile_size,
+                            matmul_desc.packmode);
+        auto matmul_param = get_matmul_kern_param(
+                param, ohw_tile_size, default_pack ? OC : oc_tile_size);
+
+        size_t packa_parallel_times = div_ceil<size_t>(
+                OC, default_pack ? matmul_desc.innerblocksize.m : oc_tile_size);
+
+        size_t packa_group_size = packA_group_size(
+                m_matmul_algo, matmul_param, matmul_desc, packa_parallel_times);
+        preprocessed_layouts.push_back(
+                {{GROUP, packa_group_size}, dtype::Int8()});
+        return preprocessed_layouts;
+    }
+    MIDOUT_END();
+    return {};
+}
+
+SmallVector<ConvBiasImpl::NCBKern>
+ConvBiasImpl::AlgoIm2col::dispatch_preprocess_kerns(
+        const NCBKernSizeParam& param) const {
+    MIDOUT_BEGIN(megdnn_fallback_im2col, 0, 3) {
+        size_t OC = param.filter_meta.ocpg;
+        size_t oc_tile_size = 0, ohw_tile_size = 0;
+        size_t GROUP = param.filter_meta.group;
+        fallback::MatrixMulImpl::AlgoBase::MatmulDescription matmul_desc =
+                m_matmul_algo->matmul_description();
+        choice_ohw_oc_block(param, oc_tile_size, ohw_tile_size,
+                            matmul_desc.innerblocksize.m,
+                            matmul_desc.innerblocksize.n, m_ohw_tile_size,
+                            matmul_desc.packmode);
+        WorkspaceBundle bundle =
+                get_bundle(param, m_matmul_algo, oc_tile_size, ohw_tile_size);
+
+        Pack_Mode packmode = matmul_desc.packmode;
+        bool default_pack = packmode == Pack_Mode::DEFAULT;
+        bool only_packA = packmode == Pack_Mode::ONLY_PACKA;
+        size_t packa_parallel_times = 0;
+
+        if (only_packA) {
+            packa_parallel_times = div_ceil<size_t>(OC, oc_tile_size);
+        } else if (default_pack) {
+            packa_parallel_times =
+                    div_ceil<size_t>(OC, matmul_desc.innerblocksize.m);
+        } else {
+            //! if nopack return null so that OprWeightPreprocessProxy can run
+            //! with nopack mode
+            return {};
+        }
+        auto matmul_param = get_matmul_kern_param(
+                param, ohw_tile_size, default_pack ? OC : oc_tile_size);
+
+        StrategyParam strategyparam;
+        strategyparam.enable_filter_preprocess =
+                is_enable_filter_preprocess(param);
+        strategyparam.packA_group_size = packA_group_size(
+                m_matmul_algo, matmul_param, matmul_desc, packa_parallel_times);
+        SmallVector<ConvBiasImpl::NCBKern> ret_kern;
+        StrategyBase* im2colstrategy =
+                Factory::get_im2col_strategy(param, m_matmul_algo);
+
+        auto kern_packA = [bundle, matmul_algo = m_matmul_algo, matmul_param,
+                           im2colstrategy, strategyparam = strategyparam,
+                           matmul_desc = matmul_desc](
+                                  const NCBKernParam& param,
+                                  const NCBKernIndex& ncb_index) mutable {
+            bundle.set(param.workspace_ptr);
+            im2colstrategy->packA_kern(bundle, param, matmul_param, matmul_algo,
+                                       ncb_index, matmul_desc, strategyparam);
+        };
+        ret_kern.push_back({kern_packA, {GROUP, packa_parallel_times}});
+        return ret_kern;
+    }
+    MIDOUT_END();
+    return {};
+}
+
 // vim: syntax=cpp.doxygen

dnn/src/fallback/conv_bias/im2col/algos.h

@@ -22,27 +22,6 @@ namespace megdnn {
 namespace fallback {
 
 class ConvBiasImpl::AlgoIm2col final : public AlgoBase {
-    //! calculate m_oc_tile_size in choice_ohw_oc_block() fucntion,
-    //! when m_oc_tile_size < this value m_oc_tile_size = ohw
-    static constexpr size_t DEFAULT_OHW_MIN_TILE_SIZE = 32;
-    //! when nr_threads > 1 and round(ohw,nr_threads)>nr_threads,
-    //! m_oc_tile_size = DEFAULT_OC_TILE_SIZE
-    static constexpr size_t DEFAULT_OC_TILE_SIZE = 512;
-    //! when m_oc_tile_size > this value m_oc_tile_size =
-    //! DEFAULT_OC_MAX_TILE_SIZE
-    static constexpr size_t DEFAULT_OC_MAX_TILE_SIZE = 1024;
-    //! when m_oc_tile_size < this value m_oc_tile_size =
-    //! DEFAULT_OC_MIN_TILE_SIZE the purpose is aligning the calculation
-    static constexpr size_t DEFAULT_OC_MIN_TILE_SIZE = 128;
-    fallback::MatrixMulImpl::KernSizeParam get_matmul_kern_param(
-            const NCBKernSizeParam& param, size_t ohw_tile_size,
-            size_t oc_tile_size) const;
-    WorkspaceBundle get_bundle(const NCBKernSizeParam& param) const;
-    void choice_ohw_oc_block(
-            const NCBKernSizeParam& param, size_t& oc_tile_size,
-            size_t& ohw_tile_size, size_t block_m, size_t block_n,
-            fallback::MatrixMulImpl::AlgoBase::PackMode pack_mode) const;
-
 public:
     AlgoIm2col(MatrixMulImpl::AlgoBase* matmul_algo, size_t ohw_tile_size)
             : m_matmul_algo(matmul_algo),
@@ -59,10 +38,16 @@ public:
     bool usable(const NCBKernSizeParam& param,
                 AlgoSelectionStrategy algo_selection_strategy) const override;
     size_t get_workspace(const NCBKernSizeParam& param) const override;
-    SmallVector<NCBKern> dispatch_kerns(
+    SmallVector<NCBKern> dispatch_kerns(const NCBKernSizeParam& param) const override;
+    SmallVector<TensorLayout> deduce_preprocessed_filter_layout(
+            const NCBKernSizeParam& param) const override;
+    size_t get_preprocess_workspace(
+            const NCBKernSizeParam& /*param*/) const override {
+        return 0;
+    }
+    SmallVector<NCBKern> dispatch_preprocess_kerns(
             const NCBKernSizeParam& param) const override;
-    bool is_preferred(
-                      const NCBKernSizeParam& param) const override {
+    bool is_preferred(const NCBKernSizeParam& param) const override {
         if (param.src_type.category() == DTypeCategory::QUANTIZED) {
             static CpuOprDelegationStorage<1> storage;
             auto conv_bias_opr = storage.get<ConvBias, 0>();

dnn/src/fallback/conv_bias/im2col/strategy_base.h

@@ -40,9 +40,11 @@ struct StrategyParam {
     size_t block_n;
     size_t block_k;
     size_t pack_oc_size;
+    size_t packA_group_size;
     bool skip_copy_dst;
     bool is_dst_8bit;
     bool is_ohw_size_bigger;
+    bool enable_filter_preprocess;
 };
 
 class StrategyBase {
@@ -62,7 +64,7 @@ public:
             const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
             const fallback::MatrixMulImpl::AlgoBase::MatmulDescription&
                     matmul_desec,
-            size_t pack_size) = 0;
+            const StrategyParam& sparam) = 0;
 
     virtual void exec_im2col(
             const WorkspaceBundle& bundle, const WorkspaceBundle& bundle_thread,
@@ -296,7 +298,7 @@ public:
             const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
             const fallback::MatrixMulImpl::AlgoBase::MatmulDescription&
                     matmul_desc,
-            size_t pack_size) override;
+            const StrategyParam& sparam) override;
     virtual void exec_im2col(
             const WorkspaceBundle& bundle, const WorkspaceBundle& bundle_thread,
             const StrategyParam& sparam,
@@ -375,7 +377,7 @@ public:
             const fallback::MatrixMulImpl::AlgoBase* matmul_algo,
             const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
             const fallback::MatrixMulImpl::AlgoBase::MatmulDescription& MDsec,
-            size_t pack_size) override;
+            const StrategyParam& sparam) override;
 
     void exec_matmul(const fallback::ConvBiasImpl::NCBKernParam& param,
                      const StrategyParam& sparam, const WorkspaceBundle& bundle,
@@ -431,7 +433,7 @@ public:
             const fallback::MatrixMulImpl::AlgoBase* matmul_algo,
             const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
             const fallback::MatrixMulImpl::AlgoBase::MatmulDescription& MDsec,
-            size_t pack_size) override;
+            const StrategyParam& sparam) override;
 
     void exec_im2col(
             const WorkspaceBundle& bundle, const WorkspaceBundle& bundle_thread,

dnn/src/fallback/conv_bias/im2col/strategy_default.cpp

@@ -25,19 +25,23 @@ void Strategy<src_ctype, bias_ctype, dst_ctype, op_ctype, op_dtype,
                    const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
                    const fallback::MatrixMulImpl::AlgoBase::MatmulDescription&
                            matmul_desc,
-                   size_t) {
+                   const StrategyParam& sparam) {
     fallback::MatrixMulImpl::KernParam matmul_param;
     size_t group_id = ncb_index.ndrange_id[0];
     static_cast<fallback::MatrixMulImpl::KernSizeParam&>(matmul_param) =
             matmulparam;
-    size_t packA_group_size = matmul_algo->get_bundle(matmul_param).get_size(0);
     size_t packed_per_oc_block_size =
             round_up(matmul_param.K, matmul_desc.innerblocksize.k) *
             matmul_desc.innerblocksize.m * matmul_desc.packa_type_size;
 
     size_t a_panel_offset = ncb_index.ndrange_id[1] * packed_per_oc_block_size;
-    int8_t* a_panel = static_cast<int8_t*>(bundle.get(BUNDLE_PACKA_INDEX)) +
-                      group_id * packA_group_size + a_panel_offset;
+    int8_t* tmp_ptr =
+            sparam.enable_filter_preprocess
+                    ? static_cast<int8_t*>(
+                              param.preprocessed_filter->tensors[0].raw_ptr)
+                    : static_cast<int8_t*>(bundle.get(BUNDLE_PACKA_INDEX));
+    int8_t* a_panel =
+            tmp_ptr + group_id * sparam.packA_group_size + a_panel_offset;
     matmul_param.A_ptr =
             const_cast<src_ctype*>(param.filter<src_ctype>(group_id));
     matmul_algo->pack_A(matmul_param, a_panel, ncb_index.ndrange_id[1],
@@ -149,15 +153,20 @@ void Strategy<src_ctype, bias_ctype, dst_ctype, op_ctype, op_dtype,
     size_t packA_per_oc_block_size =
             round_up(matmul_param.K, matmul_desc.innerblocksize.k) *
             sparam.oc_tile_size * matmul_desc.packa_type_size;
-    size_t packA_group_size = matmul_algo->get_bundle(matmul_param).get_size(0);
+    size_t packA_group_size = sparam.packA_group_size;
     size_t a_panel_offset = ncb_index.ndrange_id[1] * packA_group_size +
                             ncb_index.ndrange_id[3] * packA_per_oc_block_size;
 
     void* matmul_dst = get_matmul_dst_ptr(param, bundle_thread, sparam);
 
-    src_ctype* a_panel = reinterpret_cast<src_ctype*>(
-            reinterpret_cast<uintptr_t>(bundle.get(BUNDLE_PACKA_INDEX)) +
-            a_panel_offset);
+    int8_t* tmp_ptr =
+           sparam.enable_filter_preprocess
+                    ? static_cast<int8_t*>(
+                              param.preprocessed_filter->tensors[0].raw_ptr)
+                    : static_cast<int8_t*>(bundle.get(BUNDLE_PACKA_INDEX));
+
+    src_ctype* a_panel =
+                    reinterpret_cast<src_ctype*>(tmp_ptr + a_panel_offset);
     src_ctype* b_panel =
             reinterpret_cast<src_ctype*>(reinterpret_cast<uintptr_t>(
                     bundle_thread.get(THREAD_BUNDLE_PACKB_INDEX)));

dnn/src/fallback/conv_bias/im2col/strategy_nopack.cpp

@@ -26,7 +26,7 @@ void Strategy<src_ctype, bias_ctype, dst_ctype, op_ctype, op_dtype,
                    const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
                    const fallback::MatrixMulImpl::AlgoBase::
                            MatmulDescription& /*matmul_dsec*/,
-                   size_t) {
+                   const StrategyParam&) {
     MEGDNN_MARK_USED_VAR(bundle);
     MEGDNN_MARK_USED_VAR(param);
     MEGDNN_MARK_USED_VAR(matmulparam);

dnn/src/fallback/conv_bias/im2col/strategy_onlypacka.cpp

@@ -26,7 +26,7 @@ void Strategy<src_ctype, bias_ctype, dst_ctype, op_ctype, op_dtype,
                    const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
                    const fallback::MatrixMulImpl::AlgoBase::
                            MatmulDescription& /*matmul_desc*/,
-                   size_t) {
+                   const StrategyParam& sparam) {
     fallback::MatrixMulImpl::KernParam matmul_param;
     static_cast<fallback::MatrixMulImpl::KernSizeParam&>(matmul_param) =
             matmulparam;
@@ -36,12 +36,17 @@ void Strategy<src_ctype, bias_ctype, dst_ctype, op_ctype, op_dtype,
     size_t output_block_oc_size =
             std::min(oc_tile_size, OC - ncb_index.ndrange_id[1] * oc_tile_size);
     size_t oc_cur_index = ncb_index.ndrange_id[1] * oc_tile_size;
-    size_t packA_group_size =
-            bundle.get_size(BUNDLE_PACKA_INDEX) / param.filter_meta.group;
     size_t a_panel_offset = ncb_index.ndrange_id[1] *
                             matmul_algo->get_bundle(matmul_param).get_size(0);
-    int8_t* a_panel = static_cast<int8_t*>(bundle.get(BUNDLE_PACKA_INDEX)) +
-                      group_id * packA_group_size + a_panel_offset;
+
+    int8_t* tmp_ptr =
+           sparam.enable_filter_preprocess
+                    ? static_cast<int8_t*>(
+                              param.preprocessed_filter->tensors[0].raw_ptr)
+                    : static_cast<int8_t*>(bundle.get(BUNDLE_PACKA_INDEX));
+
+    int8_t* a_panel = tmp_ptr +
+                      group_id * sparam.packA_group_size + a_panel_offset;
     matmul_param.A_ptr =
             const_cast<src_ctype*>(param.filter<src_ctype>(group_id)) +
             oc_cur_index * matmul_param.K;
@@ -60,20 +65,22 @@ void Strategy<src_ctype, bias_ctype, dst_ctype, op_ctype, op_dtype,
                     fallback::MatrixMulImpl::KernParam matmul_param,
                     const fallback::MatrixMulImpl::AlgoBase* matmul_algo,
                     const fallback::ConvBiasImpl::NCBKernIndex& ncb_index,
-                    const fallback::MatrixMulImpl::AlgoBase::
-                            MatmulDescription& /*matmul_desc*/
-        ) {
-    size_t packA_group_size =
-            bundle.get_size(BUNDLE_PACKA_INDEX) / param.filter_meta.group;
+                    const fallback::MatrixMulImpl::AlgoBase::MatmulDescription&
+                            /*matmul_desc*/) {
     size_t a_panel_offset = ncb_index.ndrange_id[3] *
                             matmul_algo->get_bundle(matmul_param).get_size(0);
-    a_panel_offset = sparam.group_id * packA_group_size + a_panel_offset;
+    a_panel_offset =
+            sparam.group_id * sparam.packA_group_size + a_panel_offset;
 
     void* matmul_dst = get_matmul_dst_ptr(param, bundle_thread, sparam);
 
-    src_ctype* a_panel = reinterpret_cast<src_ctype*>(
-            reinterpret_cast<uintptr_t>(bundle.get(BUNDLE_PACKA_INDEX)) +
-            a_panel_offset);
+    int8_t* tmp_ptr =
+            sparam.enable_filter_preprocess
+                    ? static_cast<int8_t*>(
+                              param.preprocessed_filter->tensors[0].raw_ptr)
+                    : static_cast<int8_t*>(bundle.get(BUNDLE_PACKA_INDEX));
+
+    src_ctype* a_panel = reinterpret_cast<src_ctype*>(tmp_ptr + a_panel_offset);
     src_ctype* b_panel = nullptr;
 
     src_ctype* im2col_dst = static_cast<src_ctype*>(

dnn/src/fallback/conv_bias/opr_impl.cpp

@@ -154,7 +154,8 @@ void ConvBiasImpl::exec_preprocess(const TensorLayout& src_layout,
             bias{nullptr, bias_layout};
     auto fparam = make_ncb_kern_param(src, filter, bias, dst, workspace,
                                       preprocessed_filter);
-    ConvolutionImpl::Algorithm* algo = get_algorithm(fparam, workspace.size);
+    //! should not pass workspace_size limit otherwise can not find match algo
+    ConvBiasImpl::Algorithm* algo = get_algorithm(fparam);
     if (!is_naive_algo(algo) && NCB_ALGO_FUNC(get_preprocess_workspace, algo,
                                               fparam) <= workspace.size) {
         exec_preprocess_with_ncb_kern(fparam, algo);

dnn/src/fallback/conv_bias/opr_impl.h

@@ -299,6 +299,11 @@ private:
             const PreprocessedFilter* preprocessed_filter);
 };
 
+inline bool is_enable_filter_preprocess(
+        const ConvBiasImpl::NCBKernSizeParam& param) {
+    return param.preprocessed_filter &&
+           param.preprocessed_filter->tensors.size() >= 1;
+}
 }  // namespace fallback
 }  // namespace megdnn
 

dnn/src/fallback/convolution/opr_impl.cpp

@@ -109,7 +109,9 @@ void ConvolutionImpl::exec_preprocess(const TensorLayout& src_layout,
     TensorND src{nullptr, src_layout}, dst{nullptr, dst_layout};
     auto fparam = make_ncb_kern_param(src, filter, dst, preprocessed_filter,
                                       workspace);
-    ConvolutionImpl::Algorithm* algo = get_algorithm(fparam, workspace.size);
+
+    //! should not pass workspace_size limit otherwise can not find match algo
+    ConvolutionImpl::Algorithm* algo = get_algorithm(fparam);
     if (!is_naive_algo(algo) && NCB_ALGO_FUNC(get_preprocess_workspace, algo,
                                               fparam) <= workspace.size) {
         exec_preprocess_with_ncb_kern(fparam, algo);

dnn/test/arm_common/conv_bias_multi_thread.cpp

@@ -1837,6 +1837,21 @@ void checker_conv_bias(std::vector<conv_bias::TestArg> args, Handle* handle,
                 {arg.src, arg.filter, arg.bias, {}, {}});
     }
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COL_FP32_STRIDE2_PREPROCESS) {
+#define cb(name)                                                               \
+    check_conv_bias_preprocess(                                                \
+            get_conv_bias_args({1, 2, 3, 4, 5, 6, 7}, 2, false, false, false), \
+            handle(), nullptr, 0.001, dtype::Float32(), dtype::Float32(),      \
+            dtype::Float32(), dtype::Float32(), name);
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_F32K8X12X1") 
+    cb("IM2COLMATMUL:AARCH64_F32K4X16X1")
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARMV7_F32")
+#endif
+#undef cb
+}
 // clang-format off
 TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COL_FP32_STRIDE2) {
 #define cb(name)                                                               \
@@ -1851,6 +1866,22 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COL_FP32_STRIDE2) {
     cb("IM2COLMATMUL:ARMV7_F32")
 #endif
 #undef cb
+
+}
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COL_FP32_STRIDE1_PREPROCESS) {
+#define cb(name)                                                            \
+    check_conv_bias_preprocess(                                             \
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, false, false), \
+            handle(), nullptr, 0.001, dtype::Float32(), dtype::Float32(),   \
+            dtype::Float32(), dtype::Float32(), name);
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_F32K8X12X1") 
+    cb("IM2COLMATMUL:AARCH64_F32K4X16X1")
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARMV7_F32")
+#endif
+#undef cb
 }
 
 TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COL_FP32_STRIDE1) {
@@ -1899,6 +1930,37 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM) {
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                                       \
+    check_conv_bias_preprocess(get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, false, \
+                                         false, true, true),                           \
+                      handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),               \
+                      dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f),            \
+                      dtype::QuantizedS8(60.25f), name);                               \
+    check_conv_bias_preprocess(                                                        \
+            get_conv_bias_args({1}, 2, false, false, false, true, true),               \
+            handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),                         \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f),                      \
+            dtype::QuantizedS8(60.25f), name);
+
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+#if __ARM_FEATURE_DOTPROD
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_K8X12X4_DOTPROD");
+#else
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_K8X8X8");
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_K4X4X16");
+#endif
+#elif MEGDNN_ARMV7
+    epsilon = 1;
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_K4X8X8");
+#endif
+#undef cb
+}
+
+
 #if __ARM_FEATURE_DOTPROD
 
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_MK4_DOT) {
@@ -1924,6 +1986,29 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_MK4_DOT) {
 #endif
 #undef cb
 }
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_MK4_DOT_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                                        \
+    check_conv_bias_preprocess(get_nchw44_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false,  \
+                                                false, false, false, true),             \
+                      handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),                \
+                      dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f),             \
+                      dtype::QuantizedS8(60.25f), name);                                \
+    checker_conv_bias(                                                                  \
+            get_nchw44_conv_bias_args({1}, 2, false, true, true, false, true),          \
+            handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),                          \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f),                       \
+            dtype::QuantizedS8(60.25f), name);
+
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_8X12X4_DOTPROD:96");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:AARCH32_INT8_MK4_8X4X4_DOTPROD:96");
+#endif
+#undef cb
+}
 
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_MK4_DOT_S2_FUSE) {
     UniformIntRNG rng{-50, 50};
@@ -1968,6 +2053,31 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_S8x8x32_MK4_DOT) {
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_S8x8x32_MK4_DOT_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_nchw44_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, false,    \
+                                      true, false, true, false, false, true), \
+            handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),                \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f), {}, name);  \
+    check_conv_bias_preprocess(                                               \
+            get_nchw44_conv_bias_args({1}, 2, false, true, true, false, true, \
+                                      false, false, true),                    \
+            handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),                \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f), {}, name);
+
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_8X12X4_DOTPROD:96");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:AARCH32_INT8_MK4_8X4X4_DOTPROD:96");
+#endif
+#undef cb
+}
+
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32_MK4_DOT) {
     UniformIntRNG rng{-50, 50};
 
@@ -1992,6 +2102,30 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32_MK4_DOT) {
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32_MK4_DOT_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_nchw44_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, false,    \
+                                      true, false, true, false, false, true), \
+            handle(), &rng, epsilon, dtype::Int8(), dtype::Int8(),            \
+            dtype::Int32(), {}, name);                                        \
+    check_conv_bias_preprocess(                                               \
+            get_nchw44_conv_bias_args({1}, 2, false, true, true, false, true, \
+                                      false, false, true),                    \
+            handle(), &rng, epsilon, dtype::Int8(), dtype::Int8(),            \
+            dtype::Int32(), {}, name);
+
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_8X12X4_DOTPROD:96");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:AARCH32_INT8_MK4_8X4X4_DOTPROD:96");
+#endif
+#undef cb
+}
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_CONV1x1_QUANTIZEDSYM_MK4_DOT) {
     UniformIntRNG rng{-50, 50};
 
@@ -2055,6 +2189,41 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUANTIZEDASYM) {
 #endif
 #undef cb
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS,
+       CONV_BIAS_IM2COLMATMUL_QUANTIZEDASYM_FILTERPREPROCESS) {
+    NormalRNG rng(128.f);
+
+#define cb(name)                                                           \
+    check_conv_bias_preprocess(                                            \
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, false, false, \
+                               true, true),                                \
+            handle(), &rng, epsilon,                                       \
+            dtype::Quantized8Asymm(1.2f, (uint8_t)125),                    \
+            dtype::Quantized8Asymm(1.3f, (uint8_t)129),                    \
+            dtype::QuantizedS32(1.2 * 1.3),                                \
+            dtype::Quantized8Asymm(50.3f, (uint8_t)120), name);            \
+    check_conv_bias_preprocess(                                            \
+            get_conv_bias_args({1}, 2, false, false, false, true, true),   \
+            handle(), &rng, epsilon,                                       \
+            dtype::Quantized8Asymm(1.2f, (uint8_t)125),                    \
+            dtype::Quantized8Asymm(1.3f, (uint8_t)129),                    \
+            dtype::QuantizedS32(1.2 * 1.3),                                \
+            dtype::Quantized8Asymm(50.3f, (uint8_t)120), name);
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+#if __ARM_FEATURE_DOTPROD
+    cb("IM2COLMATMUL:AARCH64_QUINT8_K8X8X4_DOTPROD");
+#else
+    cb("IM2COLMATMUL:AARCH64_QUINT8_K8X8X8");
+#endif
+#elif MEGDNN_ARMV7
+    epsilon = 1;
+    cb("IM2COLMATMUL:ARMV7_QUINT8_K4X8X8");
+#endif
+#undef cb
+}
+
 #endif
 
 #if MEGDNN_AARCH64 || MEGDNN_ARMV7
@@ -2088,6 +2257,39 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUINT8x8x32) {
 #endif
 #undef cb
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QUINT8x8x32_FILTERPREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+    float epsilon = 0.001;
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, true, true),     \
+            handle(), &rng, epsilon,                                          \
+            dtype::Quantized8Asymm(1.2f, (uint8_t)125),                       \
+            dtype::Quantized8Asymm(1.3f, (uint8_t)129),                       \
+            dtype::QuantizedS32(1.2 * 1.3), {}, name);                        \
+    check_conv_bias_preprocess(get_conv_bias_args({1}, 2, false, true, true), \
+                               handle(), &rng, epsilon,                       \
+                               dtype::Quantized8Asymm(1.2f, (uint8_t)125),    \
+                               dtype::Quantized8Asymm(1.3f, (uint8_t)129),    \
+                               dtype::QuantizedS32(1.2 * 1.3), {}, name);
+
+#if MEGDNN_AARCH64
+#if __ARM_FEATURE_DOTPROD
+    cb("IM2COLMATMUL:AARCH64_QUINT8_K8X8X4_DOTPROD");
+#else
+    cb("IM2COLMATMUL:AARCH64_QUINT8_K8X8X8");
+#endif
+#elif MEGDNN_ARMV7
+#if __ARM_FEATURE_DOTPROD
+    cb("IM2COLMATMUL:AARCH32_QUINT8_K4X8X4");
+#endif
+    cb("IM2COLMATMUL:ARMV7_QUINT8_K4X8X8");
+#endif
+#undef cb
+}
+
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COLMATMUL_INT8x8x16) {
     UniformIntRNG rng{-50, 50};
     float epsilon = 0.001;
@@ -2127,6 +2329,51 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COLMATMUL_INT8x8x16) {
 #undef cb
 #undef cb_nchw44
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COLMATMUL_INT8x8x16_FILTERPREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+    float epsilon = 0.001;
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, true, true),     \
+            handle(), &rng, epsilon, dtype::Int8{}, dtype::Int8{},            \
+            dtype::Int16{}, dtype::Int16{}, name);                            \
+    check_conv_bias_preprocess(get_conv_bias_args({1}, 2, false, true, true), \
+                               handle(), &rng, epsilon, dtype::Int8{},        \
+                               dtype::Int8{}, dtype::Int16{}, dtype::Int16{}, \
+                               name);
+
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X16_K8X8X8");
+    cb("IM2COLMATMUL:AARCH64_INT8X8X16_K4X4X16");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARMV7_INT8X8X16_K4X8X8");
+    cb("IM2COLMATMUL:ARMV7_INT8X8X16_K4X2X16");
+#endif
+#undef cb
+}
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONVBIAS_IM2COLMATMUL_INT8x8x16_NOPACK_FILTERPREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+    float epsilon = 0.001;
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, true, true),     \
+            handle(), &rng, epsilon, dtype::Int8{}, dtype::Int8{},            \
+            dtype::Int16{}, dtype::Int16{}, name);                            \
+    check_conv_bias_preprocess(get_conv_bias_args({1}, 2, false, true, true), \
+                               handle(), &rng, epsilon, dtype::Int8{},        \
+                               dtype::Int8{}, dtype::Int16{}, dtype::Int16{}, \
+                               name);
+
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:ARM_COMMON_INT8X8X16");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARM_COMMON_INT8X8X16");
+#endif
+#undef cb
+}
+
 #endif
 
 #if __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
@@ -2154,6 +2401,31 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_FP16) {
 #endif
 #undef cb
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_FP16_FILTERPREPROCESS) {
+    using namespace conv_bias;
+
+    param::ConvBias cur_param;
+
+    std::vector<conv_bias::TestArg> args =
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, false, false);
+    std::vector<conv_bias::TestArg> args1 =
+            get_conv_bias_args({1}, 2, false, false, false);
+    args.insert(args.begin(), args1.begin(), args1.end());
+
+    NormalRNG rng(1);
+#define cb(name)                                                             \
+    check_conv_bias_preprocess(args, handle(), &rng, 0.03, dtype::Float16{}, \
+                               dtype::Float16{}, dtype::Float16{},           \
+                               dtype::Float16{}, name);
+
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_F16_K8X24X1");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:AARCH32_F16_K4X16X1");
+#endif
+#undef cb
+}
 #endif
 
 void checker_conv_bias_mul_int8x8x32(std::vector<conv_bias::TestArg> args,
@@ -2185,6 +2457,36 @@ void checker_conv_bias_mul_int8x8x32(std::vector<conv_bias::TestArg> args,
     }
 }
 
+void checker_conv_bias_int8x8x32_preprocess(std::vector<conv_bias::TestArg> args,
+                                     Handle* handle, const char* algo_name) {
+    using namespace conv_bias;
+
+    Checker<ConvBiasForward, OprWeightPreprocessProxy<ConvBiasForward>> checker(
+            handle);
+    checker.set_before_exec_callback(
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name));
+    checker.set_dtype(0, dtype::Int8());
+    checker.set_dtype(1, dtype::Int8());
+    checker.set_dtype(2, dtype::Int32());
+    checker.set_dtype(4, dtype::Int32());
+    for (auto&& arg : args) {
+        checker.set_param(arg.param).execs({arg.src, arg.filter, {}, {}, {}});
+    }
+
+    UniformIntRNG rng{-50, 50};
+    for (auto&& arg : args) {
+        checker.set_dtype(0, dtype::QuantizedS8(2.5f))
+                .set_dtype(1, dtype::QuantizedS8(2.5f))
+                .set_dtype(2, dtype::QuantizedS32(6.25f))
+                .set_dtype(4, {})
+                .set_rng(0, &rng)
+                .set_rng(1, &rng)
+                .set_rng(2, &rng)
+                .set_param(arg.param)
+                .execs({arg.src, arg.filter, {}, {}, {}});
+    }
+}
+
 #if MEGDNN_AARCH64 || MEGDNN_ARMV7
 #if !__ARM_FEATURE_DOTPROD
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32NCHW44_S2) {
@@ -2201,6 +2503,20 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32NCHW44_S2) {
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32NCHW44_S2_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<conv_bias::TestArg> args =
+            get_nchw44_conv_bias_args({2, 5, 7}, 2, false, true, true);
+
+#define cb(name) checker_conv_bias_int8x8x32_preprocess(args, handle(), name);
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_4X4X16:96");
+#else
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_MK4_4X2X16:96");
+#endif
+#undef cb
+}
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32NCHW44_S1) {
     using namespace conv_bias;
     std::vector<conv_bias::TestArg> args =
@@ -2216,6 +2532,21 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32NCHW44_S1) {
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32NCHW44_S1_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<conv_bias::TestArg> args =
+            get_nchw44_conv_bias_args({3, 4, 6}, 1, false, true, true);
+
+#define cb(name) checker_conv_bias_int8x8x32_preprocess(args, handle(), name);
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_4X4X16:96");
+#else
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_MK4_4X2X16:96");
+#endif
+
+#undef cb
+}
+
 TEST_F(ARM_COMMON_MULTI_THREADS,
        CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44_S2) {
     UniformIntRNG rng{-50, 50};
@@ -2235,6 +2566,25 @@ TEST_F(ARM_COMMON_MULTI_THREADS,
 }
 
 TEST_F(ARM_COMMON_MULTI_THREADS,
+       CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44_S2_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_nchw44_conv_bias_args({3, 4, 6}, 2), handle(), &rng, epsilon, \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS8(2.5f),               \
+            dtype::QuantizedS32(6.25f), dtype::QuantizedS8(60.25f), name);
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_4X4X16:96");
+#else
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_MK4_4X2X16:96");
+#endif
+#undef cb
+}
+
+
+TEST_F(ARM_COMMON_MULTI_THREADS,
        CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44_S1) {
     UniformIntRNG rng{-50, 50};
 
@@ -2252,6 +2602,24 @@ TEST_F(ARM_COMMON_MULTI_THREADS,
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS,
+       CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44_S1_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                              \
+    check_conv_bias_preprocess(                                               \
+            get_nchw44_conv_bias_args({2, 5, 7}, 1), handle(), &rng, epsilon, \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS8(2.5f),               \
+            dtype::QuantizedS32(6.25f), dtype::QuantizedS8(60.25f), name);
+    float epsilon = 0.001;
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_4X4X16:96");
+#else
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_MK4_4X2X16:96");
+#endif
+#undef cb
+}
+
 #if MEGDNN_AARCH64
 TEST_F(ARM_COMMON_MULTI_THREADS,
        CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44_FUSE) {
@@ -2266,6 +2634,21 @@ TEST_F(ARM_COMMON_MULTI_THREADS,
     cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_4X4X16:96");
 #undef cb
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS,
+       CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44_FUSE_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                        \
+    check_conv_bias_preprocess(                                         \
+            get_nchw44_conv_bias_args({3}, 1), handle(), &rng, epsilon, \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS8(2.5f),         \
+            dtype::QuantizedS32(6.25f), dtype::QuantizedS8(60.25f), name);
+    float epsilon = 0.001;
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_4X4X16:96");
+#undef cb
+}
+
 #endif
 #endif
 #endif
@@ -2287,6 +2670,23 @@ TEST_F(ARM_COMMON_MULTI_THREADS,
     cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_8X12X4_DOTPROD:96");
 #undef cb
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS,
+       CONV_BIAS_IM2COLMATMUL_QUANTIZEDSYM_NCHW44DOT_FUSE_PREPROCESS) {
+    UniformIntRNG rng{-50, 50};
+
+#define cb(name)                                                          \
+    check_conv_bias_preprocess(                                           \
+            get_nchw44_conv_bias_args({3}, 1, false, false, false, false, \
+                                      true, false, false, false),         \
+            handle(), &rng, epsilon, dtype::QuantizedS8(2.5f),            \
+            dtype::QuantizedS8(2.5f), dtype::QuantizedS32(6.25f),         \
+            dtype::QuantizedS8(60.25f), name);
+    float epsilon = 0.001;
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_MK4_8X12X4_DOTPROD:96");
+#undef cb
+}
+
 #endif
 #endif
 
@@ -2320,6 +2720,36 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8x8x32) {
 #undef cb
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8X8X32_FILTER_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<conv_bias::TestArg> args =
+            get_conv_bias_args({2, 3, 4, 5, 6, 7}, 1, false, true, true);
+    std::vector<conv_bias::TestArg> args1 =
+            get_conv_bias_args({1}, 2, false, true, true);
+    args.insert(args.begin(), args1.begin(), args1.end());
+
+#define cb(name) checker_conv_bias_int8x8x32_preprocess(args, handle(), name);
+
+#if MEGDNN_AARCH64
+#if __ARM_FEATURE_DOTPROD
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_K8X12X4_DOTPROD");
+#else
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_K8X8X8");
+    cb("IM2COLMATMUL:AARCH64_INT8X8X32_K4X4X16");
+#endif
+#elif MEGDNN_ARMV7
+#if __ARM_FEATURE_DOTPROD
+    cb("IM2COLMATMUL:AARCH32_INT8_K6X8X4");
+#endif
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_K4X8X8");
+#endif
+
+#if MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARMV7_INT8X8X32_K4X2X16");
+#endif
+#undef cb
+}
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COL_S1_MK4_PACK_F32) {
     using namespace conv_bias;
     std::vector<conv_bias::TestArg> args = get_nchw44_conv_bias_args(
@@ -2331,25 +2761,62 @@ TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COL_S1_MK4_PACK_F32) {
 #endif
 }
 
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COL_S1_MK4_PACK_F32_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<conv_bias::TestArg> args = get_nchw44_conv_bias_args(
+            {2, 4, 7}, 1, false, false, false, false, false, true,true);
+#define cb(name)                                                   \
+    check_conv_bias_preprocess(args, handle(), nullptr, 0.001,     \
+                               dtype::Float32(), dtype::Float32(), \
+                               dtype::Float32(), dtype::Float32(), name);
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_F32_MK4_K8X12X1");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARMV7_F32_MK4_PACK_4X12");
+#endif
+#undef cb
+}
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COL_S2_MK4_PACK_F32) {
     using namespace conv_bias;
     std::vector<conv_bias::TestArg> args = get_nchw44_conv_bias_args(
             {3, 5, 6}, 2, false, false, false, false, false, true, true);
+#define cb(name) check_conv_bias(args, handle(), name);
 #if MEGDNN_AARCH64
-    check_conv_bias(args, handle(), "IM2COLMATMUL:AARCH64_F32_MK4_K8X12X1");
+    cb("IM2COLMATMUL:AARCH64_F32_MK4_K8X12X1");
 #elif MEGDNN_ARMV7
-    check_conv_bias(args, handle(), "IM2COLMATMUL:ARMV7_F32_MK4_PACK_4X12");
+    cb("IM2COLMATMUL:ARMV7_F32_MK4_PACK_4X12");
 #endif
+#undef cb
 }
+
+TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COL_S2_MK4_PACK_F32_FUSE_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<conv_bias::TestArg> args = get_nchw44_conv_bias_args(
+            {3}, 2, false, false, false, false, false, true, true, false);
+#define cb(name)                                                   \
+    check_conv_bias_preprocess(args, handle(), nullptr, 0.001,     \
+                               dtype::Float32(), dtype::Float32(), \
+                               dtype::Float32(), dtype::Float32(), name);
+#if MEGDNN_AARCH64
+    cb("IM2COLMATMUL:AARCH64_F32_MK4_K8X12X1");
+#elif MEGDNN_ARMV7
+    cb("IM2COLMATMUL:ARMV7_F32_MK4_PACK_4X12");
+#endif
+#undef cb
+}
+
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_IM2COL_S2_MK4_PACK_F32_FUSE) {
     using namespace conv_bias;
     std::vector<conv_bias::TestArg> args = get_nchw44_conv_bias_args(
             {3}, 2, false, false, false, false, false, true, true, false);
+#define cb(name) check_conv_bias(args, handle(), name);
 #if MEGDNN_AARCH64
-    check_conv_bias(args, handle(), "IM2COLMATMUL:AARCH64_F32_MK4_K8X12X1");
+    cb("IM2COLMATMUL:AARCH64_F32_MK4_K8X12X1");
 #elif MEGDNN_ARMV7
-    check_conv_bias(args, handle(), "IM2COLMATMUL:ARMV7_F32_MK4_PACK_4X12");
+    cb("IM2COLMATMUL:ARMV7_F32_MK4_PACK_4X12");
 #endif
+#undef cb
 }
 /***************************** Conv1x1 Algo Test ***********************/
 TEST_F(ARM_COMMON_MULTI_THREADS, CONV_BIAS_1X1_S1_F32) {

dnn/test/common/conv_bias.cpp

@@ -1118,6 +1118,30 @@ void checker_conv_bias_int8x8x16(std::vector<conv_bias::TestArg> args,
     }
 }
 
+void check_conv_bias_preprocess(std::vector<conv_bias::TestArg> args,
+                                Handle* handle, RNG* rng, float epsilon,
+                                DType type0, DType type1, DType type2,
+                                DType type3, const char* algo_name) {
+    using namespace conv_bias;
+
+    Checker<ConvBiasForward, OprWeightPreprocessProxy<ConvBiasForward>> checker(
+            handle);
+    checker.set_dtype(0, type0);
+    checker.set_dtype(1, type1);
+    checker.set_dtype(2, type2);
+    checker.set_dtype(4, type3);
+    checker.set_epsilon(epsilon);
+    if (NULL != rng) {
+        checker.set_rng(0, rng).set_rng(1, rng).set_rng(2, rng).set_rng(3, rng);
+    }
+    checker.set_before_exec_callback(
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name));
+    for (auto&& arg : args) {
+        checker.set_param(arg.param).execs(
+                {arg.src, arg.filter, arg.bias, {}, {}});
+    }
+}
+
 
 void winograd_algo_extra_impl(const TensorNDArray& tensors, uint32_t m,
                               param::ConvBias param, Handle* handle,

dnn/test/common/conv_bias.h

@@ -58,7 +58,10 @@ std::vector<TestArg> get_int8_chwn4_tensorcore_args(size_t kernel_size);
 std::vector<TestArg> get_int8_nchw44_args(size_t kernel_size, size_t pack_size,
                                           bool compute_float32 = false,
                                           bool group_mode = false);
-
+void check_conv_bias_preprocess(std::vector<conv_bias::TestArg> args,
+                                Handle* handle, RNG* rng, float epsilon,
+                                DType type0, DType type1, DType type2,
+                                DType type3, const char* algo_name);
 template <typename Opr>
 using ConvBiasAlgoChecker = AlgoChecker<Opr>;
 

dnn/test/x86/conv_bias.cpp

@@ -752,7 +752,7 @@ TEST_F(X86_MULTI_THREADS, CONV_BIAS_DIRECT_STRIDE2) {
     }
 }
 
-TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8X8X) {
+TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8X8X32) {
     using namespace conv_bias;
     std::vector<TestArg> args;
 
@@ -842,6 +842,98 @@ TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8X8X) {
 #undef cb2
 }
 
+TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_INT8X8X32_FILTER_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<TestArg> args;
+
+    auto run = [&](size_t oc, size_t ic, size_t w, size_t h, size_t kernel,
+                   size_t p, NonlineMode nonline_mode) {
+        if (w + 2 * p < kernel || h + 2 * p < kernel)
+            return;
+        param::ConvBias param;
+        param.stride_h = 1;
+        param.stride_w = 1;
+        param.pad_h = p;
+        param.pad_w = p;
+        param.nonlineMode = nonline_mode;
+
+        //! no bias
+        args.emplace_back(param, TensorShape{1, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel}, TensorShape{});
+    };
+
+    for (size_t kernel : {2, 3, 4, 5, 6, 7})
+        for (size_t ic : {1, 4, 8, 16})
+            for (size_t oc : {1, 4, 8})
+                for (size_t p : {0, 2})
+                    for (size_t size : {20, 21, 24})
+                        for (NonlineMode nonline_mode :
+                             {NonlineMode::IDENTITY}) {
+                            run(oc, ic, size, size, kernel, p, nonline_mode);
+                        }
+    //! test OC block
+    run(2046, 1, 8, 8, 2, 0, NonlineMode::IDENTITY);
+
+    Checker<ConvBiasForward, OprWeightPreprocessProxy<ConvBiasForward>> checker(
+            handle());
+    UniformIntRNG rng{-50, 50};
+#define cb(algo_name)                                                          \
+    checker.set_before_exec_callback(                                          \
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name));              \
+    checker.set_dtype(0, dtype::Int8());                                       \
+    checker.set_dtype(1, dtype::Int8());                                       \
+    checker.set_dtype(2, dtype::Int32());                                      \
+    checker.set_dtype(4, dtype::Int32());                                      \
+    for (auto&& arg : args) {                                                  \
+        checker.set_param(arg.param).execs({arg.src, arg.filter, {}, {}, {}}); \
+    }                                                                          \
+    for (auto&& arg : args) {                                                  \
+        checker.set_dtype(0, dtype::QuantizedS8(2.5f))                         \
+                .set_dtype(1, dtype::QuantizedS8(2.5f))                        \
+                .set_dtype(2, dtype::QuantizedS32(6.25f))                      \
+                .set_dtype(4, {})                                              \
+                .set_rng(0, &rng)                                              \
+                .set_rng(1, &rng)                                              \
+                .set_rng(2, &rng)                                              \
+                .set_param(arg.param)                                          \
+                .execs({arg.src, arg.filter, {}, {}, {}});                     \
+    }
+#define cb2(algo_name)                                                         \
+    checker.set_before_exec_callback(                                          \
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name));              \
+    checker.set_dtype(0, dtype::Int8());                                       \
+    checker.set_dtype(1, dtype::Int8());                                       \
+    checker.set_dtype(2, dtype::Int16());                                      \
+    checker.set_dtype(4, dtype::Int16());                                      \
+    for (auto&& arg : args) {                                                  \
+        checker.set_param(arg.param).execs({arg.src, arg.filter, {}, {}, {}}); \
+    }
+
+#if MEGDNN_X86_WITH_MKL_DNN
+    if (megdnn::x86::is_supported(x86::SIMDType::VNNI)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_MKLDNN");
+    }
+#endif
+#if MEGDNN_X86_WITH_VNNI
+    if (megdnn::x86::is_supported(x86::SIMDType::VNNI)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_VNNI");
+    }
+#endif
+    if (megdnn::x86::is_supported(x86::SIMDType::AVX2)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_AVX2_2X4X16");
+        cb("IM2COLMATMUL:X86_INT8X8X32_AVX2_4X16X2");
+        cb2("IM2COLMATMUL:X86_INT8X8X16_AVX2");
+    }
+    if (::megdnn::x86::is_supported(::megdnn::x86::SIMDType::SSE4_2)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_SSE_4X8X2");
+        cb2("IM2COLMATMUL:X86_INT8X8X16_SSE");
+    }
+
+#undef cb
+#undef cb2
+}
+
+
 TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_FP32) {
     using namespace conv_bias;
     std::vector<TestArg> args;
@@ -950,6 +1042,61 @@ TEST_F(X86, CONV_BIAS_IM2COLMATMUL_FP32) {
 
 #undef cb
 }
+
+TEST_F(X86, CONV_BIAS_IM2COLMATMUL_FP32_NOPACK_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<TestArg> args;
+
+    auto run = [&](size_t oc, size_t ic, size_t w, size_t h, size_t kernel,
+                   size_t p, NonlineMode nonline_mode) {
+        if (w + 2 * p < kernel || h + 2 * p < kernel)
+            return;
+        param::ConvBias param;
+        param.stride_h = 1;
+        param.stride_w = 1;
+        param.pad_h = p;
+        param.pad_w = p;
+        param.nonlineMode = nonline_mode;
+
+        //! no bias
+        args.emplace_back(param, TensorShape{1, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel}, TensorShape{});
+        args.emplace_back(param, TensorShape{1, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel},
+                          TensorShape{1, oc, 1, 1});
+        args.emplace_back(
+                param, TensorShape{1, ic, h, w},
+                TensorShape{oc, ic, kernel, kernel},
+                TensorShape{1, oc, (h + 2 * p - kernel) / param.stride_h + 1,
+                            (w + 2 * p - kernel) / param.stride_w + 1});
+    };
+
+    for (size_t kernel : {2, 3, 4, 5, 6, 7})
+        for (size_t ic : {1, 4, 8, 16})
+            for (size_t oc : {1, 4, 8, 16, 300})
+                for (size_t p : {0, 2})
+                    for (size_t size : {8, 24})
+                        for (NonlineMode nonline_mode :
+                             {NonlineMode::IDENTITY, NonlineMode::RELU}) {
+                            run(oc, ic, size, size, kernel, p, nonline_mode);
+                        }
+
+    run(2046, 8, 20, 20, 3, 1, NonlineMode::IDENTITY);
+
+    Checker<ConvBiasForward, OprWeightPreprocessProxy<ConvBiasForward>> checker(
+            handle());
+#define cb(algo_name)                                             \
+    checker.set_before_exec_callback(                             \
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name)); \
+    for (auto&& arg : args) {                                     \
+        checker.set_param(arg.param).execs(                       \
+                {arg.src, arg.filter, arg.bias, {}, {}});         \
+    }
+    cb("IM2COLMATMUL:X86_F32_BLAS");
+
+#undef cb
+}
+
 #endif
 
 
@@ -1020,6 +1167,73 @@ TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_FP32_PACKA) {
 #undef cb
 }
 
+TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_FP32_PACKA_FILTER_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<TestArg> args;
+
+    auto run = [&](size_t oc, size_t ic, size_t w, size_t h, size_t kernel,
+                   size_t p, NonlineMode nonline_mode) {
+        if (w + 2 * p < kernel || h + 2 * p < kernel)
+            return;
+        param::ConvBias param;
+        param.stride_h = 1;
+        param.stride_w = 1;
+        param.pad_h = p;
+        param.pad_w = p;
+        param.nonlineMode = nonline_mode;
+
+        //! no bias
+        args.emplace_back(param, TensorShape{1, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel}, TensorShape{});
+        args.emplace_back(param, TensorShape{1, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel},
+                          TensorShape{1, oc, 1, 1});
+        args.emplace_back(
+                param, TensorShape{1, ic, h, w},
+                TensorShape{oc, ic, kernel, kernel},
+                TensorShape{1, oc, (h + 2 * p - kernel) / param.stride_h + 1,
+                            (w + 2 * p - kernel) / param.stride_w + 1});
+        param.sparse = param::ConvBias::Sparse::GROUP;
+        args.emplace_back(param, TensorShape{1, 2 * ic, h, w},
+                          TensorShape{2, oc, ic, kernel, kernel},
+                          TensorShape{});
+        args.emplace_back(param, TensorShape{1, 2 * ic, h, w},
+                          TensorShape{2, oc, ic, kernel, kernel},
+                          TensorShape{1, oc * 2, 1, 1});
+
+        args.emplace_back(
+                param, TensorShape{1, 2 * ic, h, w},
+                TensorShape{2, oc, ic, kernel, kernel},
+                TensorShape{1, 2 * oc, (h + 2 * param.pad_h - kernel) / 1 + 1,
+                            (w + 2 * param.pad_w - kernel) / 1 + 1});
+    };
+
+    for (size_t kernel : {2, 3, 4, 5, 6, 7})
+        for (size_t ic : {1, 4, 8, 16})
+            for (size_t oc : {1, 4, 8, 16})
+                for (size_t p : {0, 1})
+                    for (size_t size : {8, 24})
+                        for (NonlineMode nonline_mode :
+                             {NonlineMode::IDENTITY, NonlineMode::RELU}) {
+                            run(oc, ic, size, size, kernel, p, nonline_mode);
+                        }
+
+    run(2046, 8, 20, 20, 3, 1, NonlineMode::IDENTITY);
+    Checker<ConvBiasForward, OprWeightPreprocessProxy<ConvBiasForward>> checker(
+            handle());
+#define cb(algo_name)                                             \
+    checker.set_before_exec_callback(                             \
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name)); \
+    for (auto&& arg : args) {                                     \
+        checker.set_param(arg.param).execs(                       \
+                {arg.src, arg.filter, arg.bias, {}, {}});         \
+    }
+
+    cb("IM2COLMATMUL:X86_F32_MKL_PACKA:192");
+
+#undef cb
+}
+
 /**************************** Conv1x1 PackA *************************/
 namespace {
 void checker_conv_bias(std::vector<conv_bias::TestArg> args, Handle* handle,
@@ -1169,6 +1383,77 @@ TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QINT8) {
 #undef cb
 }
 
+TEST_F(X86_MULTI_THREADS, CONV_BIAS_IM2COLMATMUL_QINT8_FILTER_PREPROCESS) {
+    using namespace conv_bias;
+    std::vector<TestArg> args;
+
+    auto run = [&](size_t oc, size_t ic, size_t w, size_t h, size_t kernel,
+                   size_t p, NonlineMode nonline_mode) {
+        if (w + 2 * p < kernel || h + 2 * p < kernel)
+            return;
+        param::ConvBias param;
+        param.stride_h = 1;
+        param.stride_w = 1;
+        param.pad_h = p;
+        param.pad_w = p;
+        param.nonlineMode = nonline_mode;
+
+        //! no bias
+        args.emplace_back(param, TensorShape{1, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel}, TensorShape{});
+        //! bias channel
+        args.emplace_back(param, TensorShape{2, ic, h, w},
+                          TensorShape{oc, ic, kernel, kernel},
+                          TensorShape{1, oc, 1, 1});
+    };
+
+    for (size_t kernel : {2, 3, 4, 5, 6, 7})
+        for (size_t ic : {1, 4, 8, 16})
+            for (size_t oc : {1, 4, 8})
+                for (size_t p : {0, 2})
+                    for (size_t size : {20, 21, 24})
+                        for (NonlineMode nonline_mode :
+                             {NonlineMode::IDENTITY, NonlineMode::RELU,
+                              NonlineMode::H_SWISH}) {
+                            run(oc, ic, size, size, kernel, p, nonline_mode);
+                        }
+    run(2046, 8, 20, 20, 3, 1, NonlineMode::IDENTITY);
+    Checker<ConvBiasForward, OprWeightPreprocessProxy<ConvBiasForward>> checker(
+            handle());
+#define cb(algo_name)                                             \
+    checker.set_before_exec_callback(                             \
+            conv_bias::ConvBiasAlgoChecker<ConvBias>(algo_name)); \
+    UniformIntRNG rng{-50, 50};                                   \
+    for (auto&& arg : args) {                                     \
+        checker.set_dtype(0, dtype::QuantizedS8(2.5f))            \
+                .set_dtype(1, dtype::QuantizedS8(2.5f))           \
+                .set_dtype(2, dtype::QuantizedS32(6.25f))         \
+                .set_dtype(4, dtype::QuantizedS8(60.25))          \
+                .set_rng(0, &rng)                                 \
+                .set_rng(1, &rng)                                 \
+                .set_rng(2, &rng)                                 \
+                .set_param(arg.param)                             \
+                .execs({arg.src, arg.filter, {}, {}, {}});        \
+    }
+
+#if MEGDNN_X86_WITH_MKL_DNN
+    if (x86::is_supported(x86::SIMDType::VNNI)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_MKLDNN");
+    }
+#endif
+#if MEGDNN_X86_WITH_VNNI
+    if (x86::is_supported(x86::SIMDType::VNNI)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_VNNI");
+    }
+#endif
+    if (x86::is_supported(x86::SIMDType::AVX2)) {
+        cb("IM2COLMATMUL:X86_INT8X8X32_AVX2_2X4X16");
+    }
+
+#undef cb
+}
+
+
 TEST_F(X86, CONV_BIAS_MATMUL) {
     using namespace conv_bias;
     std::vector<TestArg> args;