================
@@ -144,6 +145,73 @@ struct Embedding {
using InstEmbeddingsMap = DenseMap<const Instruction *, Embedding>;
using BBEmbeddingsMap = DenseMap<const BasicBlock *, Embedding>;
+/// Generic storage class for section-based vocabularies.
+/// VocabStorage provides a generic foundation for storing and accessing
+/// embeddings organized into sections.
+class VocabStorage {
+private:
+ /// Section-based storage
+ std::vector<std::vector<Embedding>> Sections;
+
+ size_t TotalSize = 0;
+ unsigned Dimension = 0;
+
+public:
+ /// Default constructor creates empty storage (invalid state)
+ VocabStorage() : Sections(), TotalSize(0), Dimension(0) {}
+
+ /// Create a VocabStorage with pre-organized section data
+ VocabStorage(std::vector<std::vector<Embedding>> &&SectionData);
+
+ VocabStorage(VocabStorage &&) = default;
+ VocabStorage &operator=(VocabStorage &&Other);
+
+ VocabStorage(const VocabStorage &) = delete;
+ VocabStorage &operator=(const VocabStorage &) = delete;
+
+ /// Get total number of entries across all sections
+ size_t size() const { return TotalSize; }
+
+ /// Get number of sections
+ unsigned getNumSections() const {
+ return static_cast<unsigned>(Sections.size());
+ }
+
+ /// Section-based access: Storage[sectionId][localIndex]
+ const std::vector<Embedding> &operator[](unsigned SectionId) const {
+ assert(SectionId < Sections.size() && "Invalid section ID");
+ return Sections[SectionId];
+ }
+
+ /// Get vocabulary dimension
+ unsigned getDimension() const { return Dimension; }
+
+ /// Check if vocabulary is valid (has data)
+ bool isValid() const { return TotalSize > 0; }
+
+ /// Iterator support for section-based access
----------------
mtrofin wrote:
oh, it's an existing iteration pattern (i.e. no source change) - right?
https://github.com/llvm/llvm-project/pull/158376
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
