SCALAR UNIT WITH HIGH PERFORMANCE IN CRYPTO OPERATION
Embodiments of the invention provide a technical solution by making changes of scalar units to enable it for cryptography applications with high performance. Aspects of the invention provide a scalar unit having four 32-bit arithmetic logic units (ALUs). These four ALUs may be used as independently as four individual lanes, each generates 32-bit results. As such, the Instruction per Cycle (IPC) may be 4. In addition, these four sets of 32-bit ALUs may be configured as two 64-bit ALUs with each two of the 32-bit ALUs in one group. This configuration may, in one embodiment, generate two 64-bit results each cycle. Moreover, these four sets of 32-bit ALUs may be configured as one 128-bit ALU when the ALUs are combined as one single unit. Aspects of the invention create an output from the set of four 32-bit scalar ALUs with data width or format that is other than 32-bit.
1 . A computer-implemented method for configuring a variable data width output from a set of scalar arithmetic logic units (ALUs) comprising:
identifying a set of four 32-bit scalar ALUs in a graphics processing subsystem;
identifying input to the set of four 32-bit scalar ALUs;
connecting a controller to the set of four 32-bit scalar ALUs;
determining whether a notation in an instruction set architecture (ISA) in the input specifying a data width other than 32-bit; and
generating output based on the data width specified by the notation.
2 . The computer-implemented method of claim 1 , wherein the input comprises cryptography algorithms.
3 . The computer-implemented method of claim 1 , wherein the notation comprises identification in the Fmt4 field.
4 . The computer-implemented method of claim 1 , wherein the notation comprises ADD.i64.
5 . The computer-implemented method of claim 1 , wherein the controller comprises an on-chip memory.
6 . A graphics processing subsystem for configuring a variable data width output from a set of scalar arithmetic logic units (ALUs) comprising:
a graphics processing unit (GPU) operable to:
identifying a set of four 32-bit scalar ALUs;
identifying input to the set of four 32-bit scalar ALUs;
connecting a controller to the set of four 32-bit scalar ALUs;
determining whether a notation in an instruction set architecture (ISA) in the input specifying a data format other than 32-bit; and
generating output based on the data format specified by the notation.
7 . The graphics processing subsystem of claim 6 , wherein the input comprises cryptography algorithms.
8 . The graphics processing subsystem of claim 6 , wherein the notation comprises identification in the Fmt4 field.
9 . The graphics processing subsystem of claim 6 , wherein the notation comprises ADD.i64.
10 . The graphics processing subsystem of claim 6 , wherein the controller comprises an on-chip memory.
11 . A system for configuring a variable data width output from a set of scalar arithmetic logic units (ALUs) comprising:
a memory configured to store instructions for execution by an input application;
a graphics processing unit (GPU) configured to execute the input application, wherein the GPU is configured to:
identifying a set of four 32-bit scalar ALUs;
identifying input to the set of four 32-bit scalar ALUs;
connecting a controller to the set of four 32-bit scalar ALUs;
determining whether a notation in an instruction set architecture (ISA) in the input specifying a data width other than 32-bit; and
generating output based on the data width specified by the notation.
12 . The system of claim 11 , wherein the input comprises cryptography algorithms.
13 . The system of claim 11 , wherein the notation comprises identification in the Fmt4 field.
14 . The system of claim 11 , wherein the notation comprises ADD.i64.
15 . The system of claim 11 , wherein the controller comprises an on-chip memory.
16 . The system of claim 11 , wherein the input application comprises cryptography application.