International Business Machines Corporation

Ramyanshu Datta

Robert K Montoye

Hung Cai Ngo

Wendy Ann Belluomini

Chandler Todd McDowell

Harm Peter Hofstee

Jente Benedict Kuang

Gary Dale Carpenter

Matthew E Fernsler

A mechanism for accelerating test, debug and failure analysis of a multiprocessor device is provided. With the mechanism, on-chip trace logic is utilized to receive internal signals from logic provided in modules of the multiprocessor device. The modules are preferably copies of one another such that, given the same inputs, each module should operate in the same manner and generate the same output as long as the modules are operating properly. The modules are provided with the same inputs and the internal signals of the modules are traced using an on-chip trace bus and on-chip trace logic analyzer to perform the trace. The internal signals from one module are compared against another module so as to determine if there is any discrepancy which would indicate a fault. Additional pairs of modules may be compared to pinpoint a faulty module that is the source of the fault.

Accelerating test, debug and failure analysis of a multiprocessor device

A low-power shift-and-negate unit within a fused multiply-adder circuit is disclosed. The shift-and-negate unit includes a large shift stage, a coarse shift stage, a negate stage and a fine shift stage. The large shift stage receives a first set of shift signals and a group of data signals to generate a group of first intermediate signals. The coarse shift stage receives a second set of shift signals and the group of first intermediate signals to generate a group of second intermediate signals and their complement signals. The large shift stage and the coarse shift stage are executed within a first single processor cycle. The negate stage receives a complement decision signal and the group of second intermediate signals along with their complement signals to generate a group of third intermediate signals. Finally, the fine shift stage receives a third set of shift signals and the group of third intermediate signals to generate a group of output signals. The negate stage and the fine shift stage are executed within a second single processor cycle.

Shift-and-negate unit within a fused multiply-adder circuit

A 4-to-2 carry save adder using limited switching dynamic logic (LSDL) to reduce power consumption while reducing the delay of outputting the sum and carry bits. The 4-to-2 carry save adder may include a first LSDL circuit configured to output a sum bit. The carry save adder may further include a second LSDL circuit configured to output a carry bit. Both the first and second LSDL circuits use a carry generated in the current stage that was previously generated in the previous stage (next lower order bit position). Since the carry is generated in the current stage and not in the previous stage, the delay in outputting the sum and carry bits is reduced and hence the performance of carry save adders is improved. Further, since LSDL circuits were used in the carry save adder, power consumption was reduced while using a small amount of area.

4-to-2 carry save adder using limited switching dynamic logic

An integrated circuit includes a testable delay path. A transition of a delay path input signal causes a subsequent transition of a delay path output signal. A pulse generator receives the delay path input and output signals and produces a pulse signal having a pulse width indicative of the delay between the delay path input and output signal transitions. A delay line receives the pulse signal from the pulse generator. The delay line generates information indicative of the pulse signal pulse width. The delay line may include multiple stages in series where each stage reduces the pulse width of the pulse signal. The delay line may include a high skew inverter having PMOS and NMOS transistors having significantly different gains. The pulse generator is configured to produce a positive going pulse signal regardless of whether the delay path is inverting or non-inverting.

Skewed inverter delay line for use in measuring critical paths in an integrated circuit

A 4-to-2 carry save adder with a reduction in the delay of outputting the sum and carry bits. The 4-to-2 carry save adder may include a lower order full order coupled to a higher order full adder. The carry save adder may further include a logic unit coupled to the higher order full adder where the logic unit is configured to generate a carry bit to be inputted to the higher order full adder that normally would be generated from the carry save adder located in the previous stage. By generating this carry bit (carry-in bit) in the current stage and not in the previous stage, the delay of the carry-in bit inputted to the higher order full adder is reduced thereby reducing the delay of outputting the sum and carry bits by the higher order full adder.

Computing carry-in bit to most significant bit carry save adder in current stage

A method and apparatus for performing bit-aligned permute are disclosed. A select register, a pair of data registers and a target register are provided. The entries of the select register is preloaded with a set of bit indices. Each of the bit indices points to a desired bit location within the data registers. The byte information stored in the data registers are then copied to the target register according to the bit indices within the select register.

Growing community of inventors

Austin, TX, United States of America

Ramyanshu Datta