Keren/tensor slice insert alloc (#94)

This branch defines three new triton_gpu operations to partially solve #87. Below is an overview:

```
%tensor = triton_gpu.alloc_tensor : tensor<2x16x16xf16, #A>
%b = triton_gpu.insert_slice_async %a_ptr, %tensor, %offset {axis = 0 : i32, cache = 1 : i32, evict = 1 : i32, isVolatile = false} : tensor<16x16x!tt.ptr<f16>, #AL> -> tensor<2x16x16xf16, #A>
%c = triton_gpu.extract_slice %b, %offset {axis = 0 : i32} : tensor<2x16x16xf16, #A> -> tensor<16x16xf16, #A>
```

We plan to fully replace `copy_async` with `insert_slice_async`. **This hasn't been done yet.**

lib/Analysis/Membar.cpp

@@ -7,7 +7,6 @@ namespace mlir {
 
 void MembarAnalysis::run() {
   auto *operation = allocation->getOperation();
-  operation->getContext()->getOrLoadDialect<mlir::gpu::GPUDialect>();
   RegionInfo regionInfo;
   OpBuilder builder(operation);
   dfsOperation(operation, &regionInfo, &builder);