[BACKEND] Added support for mma layouts in reductions (#863)

Validated hackily by manually modifying the reduction .ttgir in my local
cache. There will be a follow-up PR adding some better testing
infrastructure to test out conversions and reductions on arbitrary
layouts.

include/triton/Dialect/TritonGPU/IR/Dialect.h

@@ -25,6 +25,10 @@ namespace gpu {
 
 unsigned getElemsPerThread(Type type);
 
+SmallVector<unsigned> getThreadsPerWarp(Attribute layout);
+
+SmallVector<unsigned> getWarpsPerCTA(Attribute layout);
+
 SmallVector<unsigned> getSizePerThread(Attribute layout);
 
 SmallVector<unsigned> getThreadsPerCTA(const Attribute &layout);

include/triton/Dialect/TritonGPU/IR/TritonGPUAttrDefs.td

@@ -326,7 +326,8 @@ def SliceEncodingAttr : DistributedEncoding<"SliceEncoding"> {
   );
 
   let extraClassDeclaration = extraBaseClassDeclaration # [{
-    SmallVector<int64_t> paddedShape(ArrayRef<int64_t> shape) const;
+    template<class T>
+    SmallVector<T> paddedShape(ArrayRef<T> shape) const;
   }];
 }