Get AMDGPU tensor ops working

Author: Katharine Hyatt

Project.toml

@@ -86,3 +86,6 @@ cuTENSOR = "011b41b2-24ef-40a8-b3eb-fa098493e9e1"
 
 [targets]
 test = ["Test", "Random", "DynamicPolynomials", "ChainRulesTestUtils", "ChainRulesCore", "cuRAND", "CUDACore", "cuTENSOR", "Aqua", "Logging", "Bumper", "Mooncake", "Enzyme", "EnzymeTestUtils", "Adapt", "JLArrays", "AMDGPU"]
+
+[sources]
+Strided = {url = "https://github.com/QuantumKitHub/Strided.jl/", rev = "ksh/gemm"}

ext/TensorOperationsAMDGPUExt.jl

@@ -8,7 +8,7 @@ using TensorOperations: TensorOperations as TO
 # Allocator
 #-------------------------------------------------------------------------------------------
 
-TO.tensoradd_type(TC, A::AnyRocArray, pA::Index2Tuple, conjA::Bool) =
+TO.tensoradd_type(TC, A::AnyROCArray, pA::Index2Tuple, conjA::Bool) =
     ROCArray{TC, TO.numind(pA)}
 
 function TO.tensoralloc_add(
@@ -37,7 +37,7 @@ end
 function TO.tensoralloc(
         ::Type{<:ROCArray{T, N}}, structure,
         ::Val{istemp}, allocator::TO.AMDAllocator
-    ) where {T, N}
+    ) where {T, N, istemp}
     return ROCArray{T, N}(undef, structure)
 end