[quidditch_snitch] Implement L1 allocation lowering #42
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This operation is used to represent L1 memory as one single large i8 memref. Allocation within L1 is then simply a `memref.view` into this memref. This PR also implements lowering it to LLVM. Note that the operation always returns the same memref descriptor, i.e. the memref being returned aliases all other memrefs returned by the operation.
Bufferization will represent L1 allocations as `memref.alloca` with the `l1_encoding` as the address space of memref types. To lower these, we need to assign offsets of the actual buffers into L1 memory. This PR implements that by collecting all such `alloca`s and replacing them with a `memref.view` into the `quidditch_snitch.l1_memory_view`.
# Conflicts: # codegen/compiler/src/Quidditch/Target/CMakeLists.txt # codegen/tools/quidditch-opt.cpp
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Bufferization will represent L1 allocations as
memref.allocawith thel1_encodingas the address space of memref types. To lower these, we need to assign offsets of the actual buffers into L1 memory. This PR implements that by collecting all suchallocas and replacing them with amemref.viewinto thequidditch_snitch.l1_memory_view.