| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
[MLIR][LLVM] Support named barrier as a global variable type in llvm dialect (#169194) Enables amdgcn.named.barrier target extension type as a global variable type in MLIR. | 8 个月前 | |
[MLIR][LLVM] Extend DIScopeForLLVMFuncOp to handle cross-file operatio… (#167844) The current DIScopeForLLVMFuncOp pass handles debug information for inlined code by processing CallSiteLoc attributes. However, some compilation scenarios compose code from multiple source files directly into a single function without generating CallSiteLoc. **Scenario:** python # a.py def kernel_a(tensor): print("a: {}", tensor) # a.py:3 jit_func_b(tensor) # Calls b.py code # b.py def func_b(tensor): print("b: {}", tensor) # b.py:7 The scenario executes Python at compile-time and directly inserts operations from b.py into the kernel function, resulting in MLIR like: mlir @kernel_a(...) { print("a: {}", %arg0) loc(#loc_a) // a.py:3 print("b: {}", %arg0) loc(#loc_b) // b.py:7 <- FileLineColLoc, not CallSiteLoc } loc(#loc_kernel) // a.py:1 #loc1 = loc("a.py":3:.) #loc2 = loc("b.py":7:.) #loc_a = loc("print"(#loc1)) #loc_b = loc("print"(#loc2)) llvm !6 = !DIFile(filename: "a.py", directory: "...") !9 = distinct !DISubprogram(name: "...", linkageName: "...", scope: !6, file: !6, line: 13, ...) !10 = !DILocation(line: 7, column: ., scope: !9) // Points to kernel's DISubprogram, not correct | 8 个月前 | |
Fix build breakage (MLIR LLVM dialect requires MLIRInferIntRangeInterface) (#168440) This MR fixes a recent build breakage by this MR: https://github.com/llvm/llvm-project/pull/166648 (Post-merge build error here: https://lab.llvm.org/buildbot/#/builders/138/builds/21929) The MLIRInferIntRangeInterface library is now a public dependency of MLIRLLVMDialect. | 8 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 8 个月前 | ||
| 8 个月前 | ||
| 8 个月前 |