IP Library Granted Patent US 7,353,244
Granted Patent B2
US 7,353,244 · App. 10/826,459 · Granted Apr 1, 2008

Dual-multiply-accumulator operation optimized for even and odd multisample calculations

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,353,244
App. No.
10/826,459
Granted
Apr 1, 2008
Kind
B2
Abstract

According to some embodiments, a dual multiply-accumulate operation optimized for even and odd multisample calculations is disclosed.

Claims (33)

1. A method of processing a signal, the method comprising:

calculating, in parallel, a first multiplication product of a first coefficient and a first sample, and a second multiplication product of the first coefficient and a second sample,

wherein the first sample is an (n)th sample and the second sample is an (n+2)th sample in a plurality of sequential samples;

accumulating subsequent multiplication products with the first multiplication product into a final product; and

producing a digitally filtered output signal based on the final product.

2. The method as recited in claim 1 , further comprising:

full scale negative testing the first sample and the second sample.

3. The method as recited in claim 1 , further comprising:

saturating the final product.

4. The method as recited in claim 1 , wherein the first sample and second sample are odd samples in the plurality of sequential samples.

5. The method as recited in claim 4 , wherein the first coefficient and second coefficient are filter coefficients.

6. The method as recited in claim 1 , wherein the first sample and second sample are even samples in the plurality of sequential samples.

7. The method as recited in claim 1 , further comprising:

calculating, in parallel, a third multiplication product of a second coefficient and a third sample and a fourth multiplication product of the second coefficient and a fourth sample; and

wherein the third sample is an (n+1)th sample and the fourth sample is an (n+3)th sample in the plurality of sequential samples.

8. The method as recited in claim 1 , further comprising:

calculating, in parallel a fifth multiplication product of a second coefficient and the first sample, and a sixth multiplication product of the second coefficient and the second sample generating a sixth product, and

accumulating in parallel, the fifth multiplication product with the first multiplication product and the sixth multiplication product with the second multiplication product.

9. The method as recited in claim 1 , wherein the calculating in parallel comprises executing a multiply accumulate single-instruction-multiple-data (SIMD) instruction.

10. An article comprising a storage medium having instructions stored thereon, the instructions operable to perform dual multiply-accumulate operations by causing a data processing system to:

calculate, in parallel, a first multiplication product of a first coefficient and a first sample, and a second multiplication product of the first coefficient and a second sample,

wherein the first sample is an (n)th sample and the second sample is an (n+2)th sample in the plurality of sequential sample;

calculate, in parallel, a third multiplication product of a second coefficient and a third sample and a fourth multiplication product of the second coefficient and a fourth sample,

wherein the third sample is an (n+1)th sample and the fourth sample is an (n+3)th sample in the plurality of sequential samples; and

produce a digitally filtered output signal based on the first, second, third and fourth multiplication products.

11. The article as recited in claim 10 , wherein the first sample and second sample are odd samples in the plurality of sequential samples.

12. The article as recited in claim 10 , wherein the first sample and second sample are even samples in the plurality of sequential samples.

13. The article as recited in claim 10 , the instructions further operable to:

calculate, in parallel a fifth multiplication product of a second coefficient and the first sample, and a sixth multiplication product of the second coefficient and the second sample;

accumulate, in parallel, the fifth multiplication product with the first multiplication product and the sixth multiplication product with the second multiplication product; and

produce a digitally filtered output signal based on the accumulation of the fifth multiplication product with the first multiplication product and the sixth multiplication product with the second multiplication product.

14. The article as recited in claim 13 , wherein the first coefficient and second coefficient are filter coefficients.

15. The article as recited in claim 10 , wherein to calculate in parallel comprises to execute a multiply accumulate single-instruction-multiple-data (SIMD) instruction.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 16, 2020
From: CAVIUM INTERNATIONAL
To: MARVELL ASIA PTE, LTD.
Reel/Frame 053475/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 20, 2020
From: MARVELL INTERNATIONAL LTD.
To: CAVIUM INTERNATIONAL
Reel/Frame 052918/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 15, 2006
From: INTEL CORPORATION
To: MARVELL INTERNATIONAL LTD.
Reel/Frame 018515/0817 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 30, 2004
From: ALDRICH, BRADLEY C.; PAVER, NIGEL C.; MAGHIELSE, WILLIAM T.
To: INTEL CORPORATION
Reel/Frame 015736/0460 →