Outer product-based matrix-vector multiplication operation apparatus for accelerating vector operation and method using the same
US-2024362297-A1 · Oct 31, 2024 · US
US9477441B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9477441-B2 |
| Application number | US-201514948943-A |
| Country | US |
| Kind code | B2 |
| Filing date | Nov 23, 2015 |
| Priority date | Jun 29, 2012 |
| Publication date | Oct 25, 2016 |
| Grant date | Oct 25, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Methods, apparatus, instructions and logic are disclosed providing double rounded combined floating-point multiply and add functionality as scalar or vector SIMD instructions or as fused micro-operations. Embodiments include detecting floating-point (FP) multiplication operations and subsequent FP operations specifying as source operands results of the FP multiplications. The FP multiplications and the subsequent FP operations are encoded as combined FP operations including rounding of the results of FP multiplication followed by the subsequent FP operations. The encoding of said combined FP operations may be stored and executed as part of an executable thread portion using fused-multiply-add hardware that includes overflow detection for the product of FP multipliers, first and second FP adders to add third operand addend mantissas and the products of the FP multipliers with different rounding inputs based on overflow, or no overflow, in the products of the FP multiplier. Final results are selected respectively using overflow detection.
Opening claim text (preview).
What is claimed is: 1. A machine implemented method comprising: detecting an executable thread portion comprising a first floating-point (FP) multiplication operation and a second FP operation, wherein the second FP operation specifies as a source operand a result of the first FP multiplication operation; encoding the first FP multiplication operation and the second FP operation as a combined FP operation comprising a rounding of the result of the first FP multiplication operation followed by the second FP operation using the rounded result as the source operand; storing the encoding of the combined FP operation; and executing the stored encoding of the combined FP operation as part of the executable thread portion instead of separately executing the first FP multiplication operation and the second FP operation. 2. The machine implemented method of claim 1 , wherein the second FP operation is a FP addition operation. 3. The machine implemented method of claim 1 , wherein the second FP operation is a FP subtraction operation. 4. The machine implemented method of claim 1 , wherein the second FP operation is a FP conversion operation. 5. The machine implemented method of claim 1 , wherein the encoding of the combined FP operation is stored as a micro-op in a micro-op storage. 6. The machine implemented method of claim 5 , wherein detecting is performed by processor execution optimization logic. 7. The machine implemented method of claim 1 , wherein the encoding of the combined FP operation is stored as an instruction set architecture (ISA) macro-instruction. 8. The machine implemented method of claim 7 , wherein the encoding of the combined FP operation is stored as an ISA macro-instruction in an instruction cache. 9. The machine implemented method of claim 8 , wherein detecting is performed by processor ISA translation logic. 10. The machine implemented method of claim 7 , wherein detecting is performed by compiler optimization logic.
Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers {(G06F7/4806, G06F7/4824, G06F7/49, G06F7/491, G06F7/544 take precedence)} · CPC title
Adding; Subtracting {(G06F7/4833, G06F7/4836 take precedence)} · CPC title
Special implementations · CPC title
Sum of products (for applications thereof, see the relevant places, e.g. G06F17/10, H03H17/00) · CPC title
Mantissa overflow or underflow in handling floating-point numbers · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.