.hip_fatbin ALU ALUs amd amdclang AmgX APU APUs AQL AXPY asm async Asynchronicity Asynchrony asynchrony backproject backtrace bfloat Bitcode bitcode bitcodes blockDim blockIdx bp builtins Builtins CAS clr compilable constexpr coroutines Ctx cuBLASLt cuCtx CUDA cuda cuDNN cuModule dataflow DCMAKE deallocate decompositions dedent denormal Dereferencing DFT dll DirectX DOI DPP dst EIGEN enqueue enqueues entrypoint entrypoints enum enums embeded extern fatbin fatbinary FDK FeDK Feldkamp foundationally framebuffer frontends fnuz FNUZ fp gedit GiB GPGPU gridDim GROMACS GWS hardcoded HC hcBLAS HIP-Clang hipcc hipCtx hipexamine hipified HIPify hipModule hipModuleLaunchKernel hipother HIPRTC hyperthreading icc IILE iGPU inlined inplace interdependencies interop interoperation interoperate interoperation Interprocess interprocess Intrinsics intrinsics IPC IPs isa iteratively Kress Lapack latencies libc libTIFF libstdc lifecycle linearizing literalinclude LOC LUID ltrace makefile Malloc malloc MALU maxregcount MiB memset multicore multigrid multithreading multitenant MALU NaN NCCL NDRange nonnegative NOP Numa ns Nsight ocp omnitrace outDir overindex overindexing oversubscription overutilized parallelizable pftrace pipelining parallelized pixelated pragmas preallocated preconditioners predefining prefetched preprocessor proj printf profilers PTX PyHIP queryable prefetching quad representable RMW rocgdb rocprofv rocTX roundtrip rst RTC RTTI rvalue SAXPY scalarizing sceneries shaders ShLo Shepp SIMT sinewave sinf SOMA SPMV structs SYCL syntaxes texel texels threadIdx tradeoffs templated toolkits transfering typedefs ULP ULPs unintuitive UMM uncoalesced unmap unmapped unmapping unnormalized unregister upscaled variadic voxel vulkan warpSize WinGDB zc