This is an archive of the discontinued LLVM Phabricator instance.

	Show First 20 Lines • Show All 226 Lines • ▼ Show 20 Lines
	}			}

	///			///
	/// Wrapper methods for the cuSparse library.			/// Wrapper methods for the cuSparse library.
	///			///

	// Some macro magic to get float/double alpha and beta on host.			// Some macro magic to get float/double alpha and beta on host.
	#define ALPHABETA(dtp, alpha, beta) \			#define ALPHABETA(dtp, alpha, beta) \
	__nv_bfloat16(alpha##bf16) = 1.0f; \			__nv_bfloat16(alpha##16bf) = 1.0f; \
	__nv_bfloat16(beta##bf16) = 1.0f; \			__nv_bfloat16(beta##16bf) = 1.0f; \
	__half(alpha##f16) = 1.0f; \			__half(alpha##16f) = 1.0f; \
	__half(beta##f16) = 1.0f; \			__half(beta##16f) = 1.0f; \
	float(alpha##f) = 1.0f; \			float(alpha##f) = 1.0f; \
	float(beta##f) = 1.0f; \			float(beta##f) = 1.0f; \
	double(alpha##d) = 1.0; \			double(alpha##d) = 1.0; \
	double(beta##d) = 1.0; \			double(beta##d) = 1.0; \
	const void *(alpha##p) = nullptr; \			const void *(alpha##p) = nullptr; \
	const void *(beta##p) = nullptr; \			const void *(beta##p) = nullptr; \
	if (dtp == CUDA_R_16BF \|\| dtp == CUDA_C_16BF) { \			if (dtp == CUDA_R_16BF \|\| dtp == CUDA_C_16BF) { \
	(alpha##p) = reinterpret_cast<void *>(&(alpha##16bf)); \			(alpha##p) = reinterpret_cast<void *>(&(alpha##16bf)); \
	▲ Show 20 Lines • Show All 189 Lines • Show Last 20 Lines

[mlir][sparse][gpu] fixing broken literal names in cuda runner macrosClosedPublic