MOVQ		p_len+16(FP), numBytes		// get number of input bytes to hash
	SHRQ		$6, numBytes			// force modulo 64 input buffer length
	SHLQ		$6, numBytes
	CMPQ		numBytes, $0			// exit early for zero-length input buffer
	JEQ		done
	ADDQ		dataPtr, numBytes		// point numBytes to end of input buffer
	VMOVDQU		(0*16)(digestPtr), state0	// load initial hash values and reorder

Task ordering can be useful in a number of scenarios:

* Enforce sequential ordering of tasks (e.g., `build` never runs before `clean`).
* Run build validations early in the build (e.g., validate I have the correct credentials before starting the work for a release build).