[Snippets] Added SplitLoops support for dynamic Loops

[Snippets] Fixed LoopInfo cloning

[Snippets] WA for ComputeBufferAllocationSize::get_allocation_size

[Snippets] Fixed dynamic increment and single increment for Eltwise Loops

[Snippets] Added dynamic SplitLoops support

[Snippets] Added debug prints to RuntimeConfig

[Snippets] Fixed 0 case in get_finalization_offset

[Snippets] Updated ValidateExpandedLoopInfo + Updated SnippetsUnitTest

[Snippets] Supported InnerSplittedLoopInfo in SplitLoops as Unified

[Snippets] DISABLED EXTRACT LOOP INVARIANTS

[Snippets] Fixed ExtractLoopInvariants

[Snippets] Fixed FuseLoops::can_be_fused

[Snippets] Fixes

src/common/snippets/include/snippets/lowered/loop_info.hpp

@@ -23,18 +23,10 @@ class LoopInfo {
     enum {UNDEFINED_DIM_IDX = std::numeric_limits<size_t>::max()};
 
     LoopInfo() = default;
-    LoopInfo(size_t work_amount, size_t increment, const std::vector<LoopPort>& entries, const std::vector<LoopPort>& exits, bool is_wa_const = false);
-    LoopInfo(size_t work_amount, size_t increment, const std::vector<ExpressionPort>& entries, const std::vector<ExpressionPort>& exits,
-             bool is_wa_const = false);
+    LoopInfo(size_t work_amount, size_t increment, const std::vector<LoopPort>& entries, const std::vector<LoopPort>& exits);
+    LoopInfo(size_t work_amount, size_t increment, const std::vector<ExpressionPort>& entries, const std::vector<ExpressionPort>& exits);
     virtual ~LoopInfo() = default;
 
-    /**
-     * @brief Clone LoopInfo with new expressions
-     * @param expr_map map of new and old expressions
-     * @return the copy
-     */
-    virtual std::shared_ptr<LoopInfo> clone_with_new_expr(const ExpressionMap& expr_map) const = 0;
-
     /**
      * @brief Check if some parameters of Loop are dynamic (undefined)
      * @return True if some parameters of Loop are unknown, False if all parameters are static
@@ -62,7 +54,7 @@ class LoopInfo {
      * @brief Returns work amount of the Loop.
      * @return m_work_amount
      */
-    size_t get_work_amount() const;
+    virtual size_t get_work_amount() const;
     /**
      * @brief Returns step of loop counter increment.
      * @return m_increment
@@ -83,17 +75,12 @@ class LoopInfo {
      * @return m_output_ports
      */
     const std::vector<LoopPort>& get_output_ports() const;
-    /**
-     * @brief Returns True if `work_amount` cannot be rewritten/updated by passes.
-     * @return m_is_work_amount_const
-     */
-    bool is_work_amount_const() const;
 
     /**
      * @brief Set m_work_amount value
      * @param work_amount - work amount of the loop
      */
-    void set_work_amount(size_t work_amount);
+    virtual void set_work_amount(size_t work_amount);
     /**
      * @brief Set m_increment value
      * @param increment - step of loop counter increment
@@ -104,13 +91,8 @@ class LoopInfo {
      * @param dim_idx - index
      */
     void set_dim_idx(size_t dim_idx);
-    /**
-     * @brief Sets `value` to `m_is_work_amount_const`
-     * @param value - value of the attribute
-     */
-    void set_work_amount_const(bool value);
 
-/**
+    /**
      * @brief Replace the current LoopPort `actual_port` with new `target_ports`
      * @param actual_port actual port
      * @param target_ports new ports. The ports order is important. Can contain `actual_port`
@@ -188,10 +170,6 @@ class LoopInfo {
     // Note: Scalars aren't input expressions but can be before first input expr in Linear IR
     std::vector<LoopPort> m_input_ports = {};
     std::vector<LoopPort> m_output_ports = {};
-
-    // TODO [143394] : All static values in compilation stage should be `is_const=True` (not only `work_amount`)
-    // If True, no one pass can rewrite the value of `m_work_amount`
-    bool m_is_work_amount_const = false;
 };
 using LoopInfoPtr = std::shared_ptr<LoopInfo>;
 
@@ -227,20 +205,20 @@ class UnifiedLoopInfo : public LoopInfo {
     UnifiedLoopInfo(size_t work_amount, size_t increment,
                     const std::vector<LoopPort>& entries, const std::vector<LoopPort>& exits,
                     const std::vector<LoopPortDesc>& in_descs, const std::vector<LoopPortDesc>& out_descs,
-                    const SpecificIterationHandlers& handlers = SpecificIterationHandlers(), bool is_wa_const = false);
+                    const SpecificIterationHandlers& handlers = SpecificIterationHandlers());
     UnifiedLoopInfo(size_t work_amount, size_t increment,
                     const std::vector<LoopPort>& entries, const std::vector<LoopPort>& exits,
-                    const SpecificIterationHandlers& handlers = SpecificIterationHandlers(), bool is_wa_const = false);
+                    const SpecificIterationHandlers& handlers = SpecificIterationHandlers());
     UnifiedLoopInfo(size_t work_amount, size_t increment,
                     const std::vector<ExpressionPort>& entries, const std::vector<ExpressionPort>& exits,
-                    const SpecificIterationHandlers& handlers = SpecificIterationHandlers(), bool is_wa_const = false);
+                    const SpecificIterationHandlers& handlers = SpecificIterationHandlers());
 
     /**
      * @brief Clone LoopInfo with new expressions
      * @param expr_map map of new and old expressions
      * @return the copy
      */
-    std::shared_ptr<LoopInfo> clone_with_new_expr(const ExpressionMap& expr_map) const override;
+    std::shared_ptr<LoopInfo> clone_with_new_expr(const ExpressionMap& expr_map) const;
 
     /**
      * @brief Check if some parameters of Loop are dynamic (undefined)
@@ -362,7 +340,7 @@ class UnifiedLoopInfo : public LoopInfo {
             caller(m_output_ports[i], m_output_port_descs[i]);
     }
 
-private:
+protected:
     /**
      * @brief Clone LoopPortDesc[actual_port_idx] `new_count` times and insert on the place of current desc
      * @param actual_port_idx index of the current descriptor/port
@@ -377,6 +355,56 @@ class UnifiedLoopInfo : public LoopInfo {
 };
 using UnifiedLoopInfoPtr = std::shared_ptr<UnifiedLoopInfo>;
 
+/**
+ * @interface InnerSplittedUnifiedLoopInfo
+ * @brief The structure describes inner splitted Loop after `SplitLoops`.
+ *        Contains pointer to outer splitted loop info. WorkAmount is equal to increment of outer splitted loop info.
+ * @ingroup snippets
+ */
+class InnerSplittedUnifiedLoopInfo : public UnifiedLoopInfo {
+public:
+    OPENVINO_RTTI("InnerSplittedUnifiedLoopInfo", "0", UnifiedLoopInfo)
+
+    InnerSplittedUnifiedLoopInfo() = default;
+    InnerSplittedUnifiedLoopInfo(size_t increment, const std::vector<LoopPort>& entries, const std::vector<LoopPort>& exits,
+                                 const std::vector<LoopPortDesc>& in_descs, const std::vector<LoopPortDesc>& out_descs,
+                                 const SpecificIterationHandlers& handlers, LoopInfoPtr outer_splitted_loop_info);
+
+    /**
+     * @brief Clone LoopInfo with new expressions
+     * @param expr_map map of new and old expressions
+     * @param new_outer_splitted_loop_info new outer splitted loop info
+     * @return the copy
+     */
+    std::shared_ptr<LoopInfo> clone_with_new_expr(const ExpressionMap& expr_map, LoopInfoPtr new_outer_splitted_loop_info) const;
+
+    /**
+     * @brief Returns work amount of the Loop.
+     * @return m_work_amount
+     */
+    size_t get_work_amount() const override;
+    /**
+     * @brief Returns OuterSplittedLoopInfo
+     * @return m_outer_splitted_loop_info
+     */
+    LoopInfoPtr get_outer_splitted_loop_info() const;
+
+    /**
+     * @brief Set m_work_amount value
+     * @param work_amount - work amount of the loop
+     */
+    void set_work_amount(size_t work_amount) override;
+    /**
+     * @brief Set m_outer_splitted_loop_info value
+     * @param outer - OuterSplittedLoopInfo
+     */
+    void set_outer_splitted_loop_info(LoopInfoPtr outer);
+
+private:
+    LoopInfoPtr m_outer_splitted_loop_info = nullptr;
+};
+using InnerSplittedUnifiedLoopInfoPtr = std::shared_ptr<InnerSplittedUnifiedLoopInfo>;
+
 /**
  * @interface ExpandedLoopInfo
  * @brief The structure describes expanded Loop (specific iterations) after unified loop decomposition into specific loop iterations.
@@ -390,14 +418,14 @@ class ExpandedLoopInfo : public LoopInfo {
     ExpandedLoopInfo(size_t work_amount, size_t increment,
                      const std::vector<LoopPort>& entries, const std::vector<LoopPort>& exits,
                      std::vector<int64_t> ptr_increments, std::vector<int64_t> final_offsets, std::vector<int64_t> data_sizes,
-                     SpecificLoopIterType type, std::shared_ptr<UnifiedLoopInfo> unified_loop_info, bool is_wa_const = false,
-                     bool evaluate_once = false);
+                     SpecificLoopIterType type, UnifiedLoopInfoPtr unified_loop_info, bool evaluate_once = false);
     /**
      * @brief Clone LoopInfo with new expressions
      * @param expr_map map of new and old expressions
+     * @param new_unified_loop_info new unified loop info
      * @return the copy
      */
-    std::shared_ptr<LoopInfo> clone_with_new_expr(const ExpressionMap& expr_map) const override;
+    std::shared_ptr<LoopInfo> clone_with_new_expr(const ExpressionMap& expr_map, UnifiedLoopInfoPtr new_unified_loop_info) const;
 
     /**
      * @brief Check if some parameters of Loop are dynamic (undefined)

src/common/snippets/include/snippets/lowered/loop_manager.hpp

@@ -98,13 +98,12 @@ class LoopManager {
                      size_t increment,
                      const std::vector<T>& entries,
                      const std::vector<T>& exits,
-                     bool set_default_handlers = true,
-                     bool is_work_amount_const = false) {
+                     bool set_default_handlers = true) {
         const auto normalized_increment = utils::is_dynamic_value(work_amount) || work_amount == 0 ? increment : std::min(increment, work_amount);
-        const auto& handlers = set_default_handlers
-                                  ? SpecificIterationHandlers(work_amount, normalized_increment)
-                                  : SpecificIterationHandlers();
-        const auto loop_info = std::make_shared<UnifiedLoopInfo>(work_amount, normalized_increment, entries, exits, handlers, is_work_amount_const);
+        const auto loop_info = std::make_shared<UnifiedLoopInfo>(work_amount, normalized_increment, entries, exits);
+        if (set_default_handlers)
+            loop_info->set_handlers(SpecificIterationHandlers(work_amount, normalized_increment, loop_info->get_dim_idx()));
+
         const auto loop_id = this->add_loop_info(loop_info);
         for (auto expr_it = loop_begin_pos; expr_it != loop_end_pos; ++expr_it) {
             insert_loop_id(*expr_it, loop_id);
@@ -131,9 +130,8 @@ class LoopManager {
                      size_t dim_idx,
                      const std::vector<T>& entries,
                      const std::vector<T>& exits,
-                     bool set_default_handlers = true,
-                     bool is_work_amount_const = false) {
-        const auto loop_id = mark_loop(loop_begin_pos, loop_end_pos, work_amount, increment, entries, exits, set_default_handlers, is_work_amount_const);
+                     bool set_default_handlers = true) {
+        const auto loop_id = mark_loop(loop_begin_pos, loop_end_pos, work_amount, increment, entries, exits, set_default_handlers);
         const auto loop_info = get_loop_info<UnifiedLoopInfo>(loop_id);
         loop_info->set_dim_idx(dim_idx);
         return loop_id;

src/common/snippets/include/snippets/lowered/pass/init_loops.hpp

@@ -24,7 +24,17 @@ class InitLoops : public Pass {
     InitLoops() = default;
     bool run(LinearIR& linear_ir) override;
 
-    static void init_loop_info(const UnifiedLoopInfoPtr& loop_info, size_t loop_id, bool only_runtime_args = false);
+    /**
+     * @brief Updates ptr_increments and finalization offsets of the provided "loop_info" based on current work amount
+     */
+    static void update_data_pointer_shifts(const UnifiedLoopInfoPtr& loop_info);
+    /**
+     * @brief Updates work amount and updates data pointer shifts of the provided "loop_info"
+     */
+    static void update_runtime_parameters(const UnifiedLoopInfoPtr& loop_info);
+
+private:
+    static void update_compile_parameters(const UnifiedLoopInfoPtr& loop_info, size_t loop_id);
 };
 
 } // namespace pass

src/common/snippets/include/snippets/lowered/pass/iter_handler.hpp

@@ -48,32 +48,14 @@ class SetFillOffset : public pass::RangedPass {
 };
 
 /**
- * @interface TransformInnerSplitLoop
- * @brief The pass updates finalization offsets, work amount and increment of inner Loop basing on tail_size of the current Loop
- * @param m_tail_size - tail_size of the current Loop
+ * @interface SetLoopIncrementOne
+ * @brief The pass set `increment = 1` to ExpandedLoopInfo which is mapped on LoopEnd in the passed iterator `end` and to this LoopEnd.
  * @ingroup snippets
  */
-class TransformInnerSplitLoop : public pass::RangedPass {
+class SetLoopIncrementOne : public snippets::lowered::pass::RangedPass {
 public:
-    TransformInnerSplitLoop(size_t tail_size);
-    OPENVINO_RTTI("TransformInnerSplitLoop", "RangedPass")
-    bool run(LinearIR& linear_ir, LinearIR::constExprIt begin, LinearIR::constExprIt end) override;
-    std::shared_ptr<pass::PassBase> merge(const std::shared_ptr<pass::PassBase>& other) override;
-
-private:
-    size_t m_tail_size;
-};
-
-/**
- * @interface SetEvaluateOnce
- * @brief The pass set `evaluate once = true` only to ExpandedLoopInfo which is mapped on LoopEnd in the passed iterator `end`.
- *        The pointer arithmetic should be updated in the separate optimization `OptimizeLoopSingleEvaluation`
- * @ingroup snippets
- */
-class SetEvaluateOnce : public snippets::lowered::pass::RangedPass {
-public:
-    SetEvaluateOnce() = default;
-    OPENVINO_RTTI("SetEvaluateOnce", "RangedPass")
+    SetLoopIncrementOne() = default;
+    OPENVINO_RTTI("SetLoopIncrementOne", "RangedPass")
     bool run(snippets::lowered::LinearIR& linear_ir,
              snippets::lowered::LinearIR::constExprIt begin,
              snippets::lowered::LinearIR::constExprIt end) override;

src/common/snippets/include/snippets/lowered/pass/split_loops.hpp

@@ -35,8 +35,24 @@ class SplitLoops : public RangedPass {
     SplitLoops();
     bool run(LinearIR& linear_ir, lowered::LinearIR::constExprIt begin, lowered::LinearIR::constExprIt end) override;
 
+    static void split(LinearIR& linear_ir, size_t loop_to_split_id, size_t outer_increment);
+
 private:
     static bool can_be_split(const UnifiedLoopInfoPtr& current, const UnifiedLoopInfoPtr& target);
+
+    /**
+     * @interface TransformInnerSplitLoop
+     * @brief The pass replace existing inner splitted LoopInfo with new InnerSplittedUnifiedLoopInfo and
+     *        update the corresponding LoopInfo
+     * @ingroup snippets
+     */
+    class TransformInnerSplitLoop : public pass::RangedPass {
+    public:
+        TransformInnerSplitLoop() = default;
+        OPENVINO_RTTI("TransformInnerSplitLoop", "RangedPass")
+        bool run(LinearIR& linear_ir, LinearIR::constExprIt begin, LinearIR::constExprIt end) override;
+        std::shared_ptr<pass::PassBase> merge(const std::shared_ptr<pass::PassBase>& other) override;
+    };
 };
 
 } // namespace pass

src/common/snippets/include/snippets/lowered/specific_loop_iter_handlers.hpp

@@ -15,7 +15,7 @@ namespace lowered {
 class SpecificIterationHandlers {
 public:
     SpecificIterationHandlers() = default;
-    SpecificIterationHandlers(size_t loop_work_amount, size_t loop_increment);
+    SpecificIterationHandlers(size_t loop_work_amount, size_t loop_increment, size_t processing_dim_idx);
     SpecificIterationHandlers(pass::PassPipeline first_iter_handlers,
                               pass::PassPipeline main_body_handlers,
                               pass::PassPipeline last_iter_handlers);

src/common/snippets/include/snippets/pass/analyze_broadcastable_inputs.hpp

@@ -12,7 +12,7 @@ namespace pass {
 
 /**
  * @interface AnalyzeBroadcastableInputs
- * @brief Analyzes body parameters which affects inputs of broadcastable operations (If needed, `Broadcast` op should be inserted there).s
+ * @brief Analyzes body parameters which affects inputs of broadcastable operations (If needed, `Broadcast` op should be inserted there).
  *        Also the pass initializes special map `BroadcastableInputsMap`
  *        Notes:
  *          - Must be called after Canonicalization pass

src/common/snippets/include/snippets/runtime_configurator.hpp

@@ -36,6 +36,10 @@ class RuntimeConfig {
         return get_type_info().name;
     }
 
+#ifdef SNIPPETS_DEBUG_CAPS
+    virtual std::string to_string() const;
+#endif
+
     size_t tensor_rank = 0;
     size_t tile_rank = 0;
 
@@ -136,7 +140,8 @@ class RuntimeConfigurator {
     std::vector<snippets::lowered::PortDescriptorPtr> m_io_descs = {};
     std::vector<size_t> m_io_data_sizes = {};
     // [cluster_id -> buffer expressions ]
-    std::map<size_t, std::set<lowered::ExpressionPtr>> m_dynamic_buffer_clusters;
+    std::map<size_t, std::set<lowered::ExpressionPtr>> m_dynamic_buffer_clusters = {};
+    std::vector<size_t> m_ordered_loop_ids = {};
 
     std::vector<ov::snippets::VectorDims> m_latest_shapes = {};
 };

src/common/snippets/src/generator.cpp

@@ -51,9 +51,11 @@ LoweringResult Generator::generate(const lowered::LinearIRPtr& linear_ir, const
     }
     result.compiled_snippet = target->get_snippet();
     result.kernel_executor_table = target->get_runtime_configurator()->get_kernel_executor_table();
-    // Some kernel executors might've been registered during code emission.
+    // In static case some kernel executors might've been registered during code emission.
     // We need to update them, so appropriate kernels will be compiled.
-    result.kernel_executor_table->update_state(linear_ir);
+    // In dynamic case it should be handled by RuntimeConfigurator
+    if (!linear_ir->is_dynamic())
+        result.kernel_executor_table->update_state(linear_ir);
 
     return result;
 }