Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 1 of 32 PageID #: 1
`
`IN THE UNITED STATES DISTRICT COURT
`FOR THE DISTRICT OF DELAWARE
`
`INVENSAS CORPORATION and TESSERA
`ADVANCED TECHNOLOGIES, INC.,
`
`
`Plaintiffs,
`
`
`
`
`NVIDIA CORPORATION,
`
`
`
`
`
`
`
`C.A. No. _____________
`
`
`JURY TRIAL DEMANDED
`
`)
`)
`)
`)
`)
`)
`)
`)
`)
`)
`
`COMPLAINT FOR PATENT INFRINGEMENT
`
`v.
`
`
`
`
`
`Defendant.
`
`
`
`
`
`Plaintiffs Invensas Corporation and Tessera Advanced Technologies, Inc. (collectively
`
`“Plaintiffs”) bring this complaint for patent infringement against Defendant NVIDIA
`
`Corporation (“NVIDIA” or “Defendant”). Plaintiffs, on personal knowledge as to their own acts,
`
`and on information and belief as to all others based on investigation, allege as follows:
`
`NATURE OF THE ACTION
`
`1.
`
`This is a civil action for infringement of United States Patent Nos. 6,232,231 (“the
`
`’231 patent”), 6,849,946 (“the ’946 patent”), 7,064,005 (“the ’005 patent”), 6,317,333 (“the ’333
`
`patent”), and 5,666,046 (“the ’046 patent”) (collectively, the “Asserted Patents”) under the patent
`
`laws of the United States, 35 U.S.C. § 1, et seq.
`
`THE PARTIES
`
`2.
`
`Plaintiff Invensas Corporation is a Delaware corporation with its principal place
`
`of business at 3025 Orchard Parkway, San Jose, California 95134.
`
`3.
`
`Plaintiff Tessera Advanced Technologies, Inc. is a Delaware corporation with its
`
`principal place of business at 3025 Orchard Parkway, San Jose, California 95134.
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 2 of 32 PageID #: 2
`
`4.
`
`Defendant NVIDIA Corporation is a Delaware corporation with its principal place
`
`of business at 2788 San Tomas Expressway, Santa Clara, California 95051. NVIDIA may be
`
`served through its registered agent, Corporation Service Company, 251 Little Falls Drive,
`
`Wilmington, Delaware 19808.
`
`JURISDICTION AND VENUE
`
`5.
`
`The Court has subject matter jurisdiction over the matters pleaded herein under 28
`
`U.S.C. §§ 1331 and 1338(a) and the patent laws of the United States, 35 U.S.C. § 1, et seq.
`
`6.
`
`The Court has personal jurisdiction over NVIDIA at least because NVIDIA is
`
`organized and exists under the laws of the State of Delaware. On information and belief,
`
`NVIDIA has regularly and systematically transacted business in and with residents of the State
`
`of Delaware, directly or through intermediaries, and/or committed acts of infringement in the
`
`State of Delaware as alleged more particularly below. NVIDIA has also placed infringing
`
`products into the stream of commerce by shipping those products into the State of Delaware or
`
`by knowing that the products would be shipped into the State of Delaware. Plaintiffs’ causes of
`
`action arise, at least in part, from NVIDIA’s contacts with and activities in the State of Delaware.
`
`7.
`
`Venue is proper in this judicial district pursuant to 28 U.S.C. §§ 1400 and 1391(b)
`
`and (c) because NVIDIA, as a Delaware corporation, resides in this judicial district. In addition,
`
`NVIDIA has committed acts of infringement in the State of Delaware, including by selling and
`
`distributing infringing products in the State of Delaware.
`
`NVIDIA’S INFRINGING PRODUCTS AND ACTIVITIES
`
`8.
`
`NVIDIA is a global supplier of graphics processing units (“GPUs”) and system-
`
`on-a-chip processors (SoCs) that incorporate GPUs and multi-core CPUs to drive
`
`supercomputing. See 2018 NVIDIA Form 10-K, p. 23. NVIDIA’s two reportable segments, GPU
`
`and Tegra Processor, are based on a single underlying graphics architecture. See id. NVIDIA’s
`
`
`
`2
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 3 of 32 PageID #: 3
`
`GPU and Tegra SoC platforms serve many markets, from consumer PC gaming to enterprise
`
`workstations to government and cloud service provider datacenters. See id., p. 9.
`
`Source: 2018 NVIDIA Form 10-K, p. 5.
`
`
`
`9.
`
`NVIDIA does not directly manufacture semiconductor wafers used for its
`
`products. Instead, NVIDIA utilizes a “fabless” manufacturing strategy, whereby NVIDIA
`
`employs third party suppliers for wafer fabrication, assembly, testing, and packaging. See 2018
`
`NVIDIA Form 10-K, p. 9. This allows NVIDIA to “focus [its] resources on product design,
`
`additional quality assurance, marketing, and customer support.” Id. On information and belief,
`
`the bulk of NVIDIA’s semiconductor wafers are fabricated by Taiwan Semiconductor
`
`Manufacturing Company Limited (“TSMC”).
`
`10.
`
`For fiscal years 2013 through 2018, NVIDIA reported global revenues of more
`
`than $34 billion. On information and belief, a substantial portion of this revenue is attributable to
`
`infringing sales made in the United States, including, without limitation: (a) NVIDIA products
`
`sold directly to consumers and companies in the United States; (b) NVIDIA products sold abroad
`
`
`
`3
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 4 of 32 PageID #: 4
`
`and with knowledge that those products would be incorporated in finished products and then
`
`imported into the United States for sale and/or use; and (c) NVIDIA products nominally sold
`
`abroad but for which substantial activities underlying the sales transactions (e.g., design-win
`
`activities, negotiations, testing, qualification) take place in the United States.
`
`11.
`
`NVIDIA acknowledges that for products not sold directly to consumers,
`
`“achieving design wins is an important success factor.” 2018 NVIDIA Form 10-K, p. 14.
`
`“Achieving design wins may involve a lengthy process in pursuit of a customer opportunity and
`
`depend on our ability to anticipate features and functionality that customers and consumers will
`
`demand.” Id. To that end, NVIDIA has deemed it critical to employ sales teams with “a high
`
`level of technical expertise and product and industry knowledge to support the competitive and
`
`complex design win process,” along with a “highly skilled team of application engineers to assist
`
`our Channel in designing, testing, and qualifying system designs that incorporate our products.”
`
`2016 NVIDIA Form 10-K, p. 7. On information and belief, the sales teams and application
`
`engineers referenced in NVIDIA’s Form 10-K filing are located primarily in the United States.
`
`12.
`
`NVIDIA also works in collaboration with industry leaders to develop products:
`
`“We invest significant resources in the development of relationships with industry leaders, often
`
`assisting these companies in the product definition of their new products. We believe that
`
`forming these relationships and utilizing next-generation development tools to design, simulate
`
`and verify our products will help us remain at the forefront of visual computing and develop
`
`products that utilize leading-edge technology on a rapid basis.” 2017 NVIDIA Form 10-K, p. 10.
`
`13.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for 40nm Fermi GPUs, including products with the part
`
`name or number GF100, GF104, GF106, GF108, GF110, GF114, GF116, GF117, GF118, and
`
`
`
`4
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 5 of 32 PageID #: 5
`
`GF119 (the “40nm Fermi GPUs”). On information and belief, NVIDIA 40nm Fermi GPUs are
`
`made using TSMC’s 40nm manufacturing technology, and therefore include the same or similar
`
`structures and features. On information and belief, NVIDIA 40nm Fermi GPUs are incorporated
`
`in products that are designed, made, used, sold, offered for sale, and/or imported into the United
`
`States, including, for example, graphics cards and/or gaming laptops sold by Acer, ASUS,
`
`Lenovo, and MSI and the following NVIDIA products:
`
`C2070 GPU Computing
`Module
`C2075 GPU Computing
`Module
`GeForce 410M
`GeForce 510
`GeForce 605
`GeForce 610M
`GeForce 710M
`GeForce 720M
`GeForce 810M
`GeForce 820M
`GeForce GT 415M
`GeForce GT 420
`GeForce GT 420M
`GeForce GT 425M
`GeForce GT 430
`GeForce GT 435M
`GeForce GT 440
`GeForce GT 445M
`GeForce GT 520
`GeForce GT 520M
`GeForce GT 520MX
`GeForce GT 525M
`GeForce GT 530
`GeForce GT 540M
`GeForce GT 545
`GeForce GT 550M
`GeForce GT 555M
`GeForce GT 610
`
`
`GeForce GT 620
`GeForce GT 620M
`GeForce GT 625
`GeForce GT 625M
`GeForce GT 630
`GeForce GT 630M
`GeForce GT 635M
`GeForce GT 640
`GeForce GT 640M LE
`GeForce GT 645
`GeForce GT 705
`GeForce GT 730
`GeForce GTS 450
`GeForce GTX 460
`GeForce GTX 460 SE
`GeForce GTX 460M
`GeForce GTX 470M
`GeForce GTX 485M
`GeForce GTX 550 Ti
`GeForce GTX 555
`GeForce GTX 560
`GeForce GTX 560 SE
`GeForce GTX 560 Ti
`GeForce GTX 560M
`GeForce GTX 570
`GeForce GTX 570M
`GeForce GTX 580
`GeForce GTX 580M
`GeForce GTX 590
`GeForce GTX 670M
`
`GeForce GTX 675M
`GeForce GTX465
`GeForce GTX470
`GeForce GTX480
`GeForce GTX480M
`M2050 GPU Module
`M2070 GPU Computing
`Module
`M2090 GPU Computing
`Module
`Quadro 1000M
`Quadro 2000
`Quadro 3000M
`Quadro 4000
`Quadro 4000M
`Quadro 5000
`Quadro 5000M
`Quadro 500M
`Quadro 5010M
`Quadro 600
`Quadro 6000
`Quadro 7000
`Quadro NVS 315
`Quadro Plex 7000
`S2050 GPU Computing
`Server
`S2070 GPU Computing
`Server
`
`14.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for 28nm Kepler GPUs, including products with the part
`5
`
`
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 6 of 32 PageID #: 6
`
`name or number GK104, GK106, GK107, GK110, and GK208 (the “28nm Kepler GPUs”). On
`
`information and belief, NVIDIA 28nm Kepler GPUs are made using TSMC’s 28nm
`
`manufacturing technology, and therefore include the same or similar structures and features. On
`
`information and belief, NVIDIA 28nm Kepler GPUs are incorporated in products that are
`
`designed, made, used, sold, offered for sale, and/or imported into the United States, including,
`
`for example, graphics cards and/or gaming laptops sold by Acer, ASUS, Lenovo, and MSI and
`
`the following NVIDIA products:
`
`GeForce 825M
`GeForce 920M
`GeForce GT 630
`GeForce GT 635
`GeForce GT 640
`GeForce GT 640M
`GeForce GT 640M LE
`GeForce GT 645M
`GeForce GT 650M
`GeForce GT 660M
`GeForce GT 710
`GeForce GT 720
`GeForce GT 720M
`GeForce GT 730
`GeForce GT 730M
`GeForce GT 735M
`GeForce GT 740
`GeForce GT 740M
`GeForce GT 745M
`GeForce GT 750M
`GeForce GT 755M
`GeForce GTX 645
`GeForce GTX 650
`GeForce GTX 650 Ti
`GeForce GTX 650 Ti
`Boost
`GeForce GTX 660
`GeForce GTX 660 Ti
`
`
`GeForce GTX 670
`GeForce GTX 680
`GeForce GTX 690
`GeForce GTX 760
`GeForce GTX 760 Ti
`GeForce GTX 760M
`GeForce GTX 765M
`GeForce GTX 770
`GeForce GTX 770M
`GeForce GTX 780
`GeForce GTX 780 Ti
`GeForce GTX 780M
`GeForce GTX 860M
`GeForce GTX 870M
`GeForce GTX 880M
`GeForce GTX TITAN
`GeForce GTX TITAN
`Black
`GeForce GTX TITAN Z
`GeForce GTX 670MX
`GeForce GTX 675MX
`GeForce GTX 680M
`GeForce GTX 680MX
`GRID K1
`GRID K2
`GRID K340
`GRID K520
`K10 GPU Accelerator
`
`K20 GPU Accelerator
`K20X GPU Accelerator
`K40 GPU Accelerator
`Quadro 410
`Quadro K1000M
`Quadro K1100M
`Quadro K2000
`Quadro K2000D
`Quadro K2000M
`Quadro K2100M
`Quadro K3000M
`Quadro K3100M
`Quadro K4000
`Quadro K4000M
`Quadro K4100M
`Quadro K420
`Quadro K4200
`Quadro K5000
`Quadro K5000M
`Quadro K500M
`Quadro K5100M
`Quadro K510M
`Quadro K5200
`Quadro K600
`Quadro K6000
`Quadro K610M
`Quadro NVS 510
`
`15.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for 28nm Maxwell GPUs, including products with the part
`6
`
`
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 7 of 32 PageID #: 7
`
`name or number GM107, GM108, GM200, GM204, and GM206 (the “28nm Maxwell GPUs”).
`
`On information and belief, NVIDIA 28nm Maxwell GPUs are made using TSMC’s 28nm
`
`manufacturing technology, and therefore include the same or similar structures and features. On
`
`information and belief, NVIDIA 28nm Maxwell GPUs are incorporated in products that are
`
`designed, made, used, sold, offered for sale, and/or imported into the United States, including,
`
`for example, graphics cards and/or gaming laptops sold by Acer, ASUS, Lenovo, and MSI and
`
`the following NVIDIA products:
`
`GeForce 840M
`GeForce 845M
`GeForce 930M
`GeForce 940M
`GeForce GT 945A
`GeForce GTX 745
`GeForce GTX 750
`GeForce GTX 750 Ti
`GeForce GTX 850M
`GeForce GTX 860M
`GeForce GTX 950
`GeForce GTX 950M
`GeForce GTX 960
`GeForce GTX 960M
`GeForce GTX 965M
`
`
`GeForce GTX 970
`GeForce GTX 970M
`GeForce GTX 980
`GeForce GTX 980 Ti
`GeForce GTX 980
`GeForce GTX 980M
`GeForce GTX TITAN X
`GeForce MX110
`GeForce MX130
`M10 GPU Accelerator
`M4 GPU Accelerator
`M40 GPU Accelerator
`Quadro K1200
`Quadro K2200
`Quadro K2200M
`
`Quadro K620
`Quadro M1000M
`Quadro M1200
`Quadro M2000
`Quadro M2000M
`Quadro M2200
`Quadro M500M
`Quadro M520
`Quadro M6000
`Quadro M600M
`Quadro M620
`Quadro NVS 810
`Jetson Nano
`
`16.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for 16nm Pascal GPUs, including products with the part
`
`name or number GP100, GP102, GP104, and GP106 (the “16nm Pascal GPUs”). On information
`
`and belief, NVIDIA 16nm Pascal GPUs are made using TSMC’s 16nm manufacturing
`
`technology, and therefore include the same or similar structures and features. On information and
`
`belief, NVIDIA 16nm Pascal GPUs are incorporated in products that are designed, made, used,
`
`sold, offered for sale, and/or imported into the United States, including, for example, graphics
`
`
`
`7
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 8 of 32 PageID #: 8
`
`cards and/or gaming laptops sold by Acer, ASUS, Lenovo, and MSI and the following NVIDIA
`
`products:
`
`GeForce GTX 1060
`GeForce GTX 1060 Max-
`Q
`GeForce GTX 1070
`GeForce GTX 1070 Max-
`Q
`GeForce GTX 1070 Ti
`GeForce GTX 1080
`GeForce GTX 1080 Max-
`Q
`
`
`
`GeForce GTX 1080 Ti
`NVIDIA TITAN X
`NVIDIA TITAN Xp
`P100 GPU Accelerator
`P4 GPU Accelerator
`P40 GPU Accelerator
`P6 GPU Accelerator
`Quadro GP100
`Quadro P3000
`Quadro P3200
`
`Quadro P4000
`Quadro P4000 Max-Q
`Quadro P4200
`Quadro P5000
`Quadro P5200
`Quadro P6000
`Jetson TX2
`
`17.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for 28nm Tegra K1 SoCs, including products with the part
`
`name or number T124 and T132 (the “28nm Tegra K1 SoCs”). The 28nm Tegra K1 SoCs
`
`feature, among other things, a 28nm Kepler GPU. On information and belief, NVIDIA 28nm
`
`Tegra K1 SoCs are made using TSMC’s 28nm manufacturing technology, and therefore include
`
`the same or similar structures and features. On information and belief, NVIDIA 28nm Tegra K1
`
`SoCs are incorporated in products that are designed, made, used, sold, offered for sale, and/or
`
`imported into the United States, including, for example, the NVIDIA SHIELD Tablet, Acer
`
`Chromebook 13, Google Nexus 9, Lenovo ThinkVision 28, and Google Project Tango Tablet.
`
`18.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for 20nm Tegra X1 SoCs, including products with the part
`
`name or number T210 and NX (the “20nm Tegra X1 SoCs”). The 20nm Tegra X1 SoCs feature,
`
`among other things, a 20nm Maxwell GPU. On information and belief, NVIDIA 20nm Tegra X1
`
`SoCs are made using TSMC’s 20nm manufacturing technology, and therefore include the same
`
`or similar structures and features. On information and belief, NVIDIA 20nm Tegra X1 SoCs are
`
`
`
`8
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 9 of 32 PageID #: 9
`
`incorporated in products that are designed, made, used, sold, offered for sale, and/or imported
`
`into the United States, including, for example, the NVIDIA SHIELD TV, NVIDIA SHIELD
`
`Tablet, NVIDIA DRIVE CX & PX, Google Pixel C, and Nintendo Switch.
`
`19.
`
`NVIDIA designs, makes, uses, sells, offers for sale, and/or imports into the
`
`United States, and provides support for the Tesla GPUs, including products with the part name or
`
`number Tesla P100 and Tesla V100 that are made using TSMC’s Chip-on-Wafer-on-Substrate
`
`(“CoWoS”) technology (the “CoWoS GPUs”). On information and belief, NVIDIA CoWoS
`
`GPUs include the same or similar structures and features. On information and belief, NVIDIA
`
`CoWoS GPUs are incorporated in products that are designed, made, used, sold, offered for sale,
`
`and/or imported into the United States, including, for example, the NVIDIA DGX-1 and DGX-2
`
`supercomputers and data center products provided by Acer, ASUSTek Computer, Cisco, Dell,
`
`Fujitsu, Google, Lenovo, Penguin Computing, and Supermicro, among others. See, e.g.,
`
`https://www.nvidia.com/en-us/data-center/where-to-buy-tesla/.
`
`CLAIMS FOR PATENT INFRINGEMENT
`
`20.
`
`Plaintiffs incorporate by reference the allegations set forth in paragraphs 1
`
`through 19 as though fully set forth herein.
`
`21.
`
`The allegations provided below are exemplary and without prejudice to Plaintiffs’
`
`infringement contentions provided pursuant to the Court’s scheduling order and local rules. In
`
`providing these allegations, Plaintiffs do not convey or imply any particular claim constructions
`
`or the precise scope of the claims. Plaintiffs’ claim construction contentions regarding the
`
`meaning and scope of the claim terms will be provided under the Court’s scheduling order and
`
`local rules.
`
`
`
`9
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 10 of 32 PageID #: 10
`
`COUNT I
`INFRINGEMENT OF U.S. PATENT NO. 6,232,231
`
`22.
`
`Plaintiffs incorporate by reference the allegations set forth in paragraphs 1
`
`through 21 as though fully set forth herein.
`
`23.
`
`On May 15, 2001, the United States Patent and Trademark Office (“USPTO”)
`
`duly and legally issued the ’231 patent, titled “Planarized Semiconductor Interconnect
`
`Topography and Method For Polishing a Metal Layer To Form Interconnect,” naming Anantha
`
`R. Sethuraman and Christopher A. Seams as inventors. A true and correct copy of the ’231
`
`patent is attached hereto as Exhibit A.
`
`24.
`
`Invensas owns the entire right, title, and interest in and to the ’231 patent,
`
`including the right to sue and recover damages, including damages for past infringement.
`
`25.
`
`Plaintiffs have complied with applicable requirements of 35 U.S.C. § 287(a),
`
`which entitles Plaintiffs to receive damages for past infringement.
`
`26.
`
`By at least December 2, 2014, Plaintiffs disclosed the existence of the ’231 patent
`
`to NVIDIA and explained, in the form of claim charts, how certain exemplary NVIDIA devices
`
`infringe one or more claims of the ’231 patent. Thus, since at least December 2, 2014, NVIDIA
`
`has had knowledge of the ’231 patent and that its activities infringe the ’231 patent. In addition,
`
`since at least December 2, 2014, NVIDIA has known or should have known that its customers,
`
`distributors, and other purchasers of the ’231 Accused Products were infringing the ’231 patent.
`
`27.
`
`NVIDIA has infringed, directly and/or indirectly, either literally or under the
`
`doctrine of equivalents, at least claim 1 of the ’231 patent in violation of at least 35 U.S.C.
`
`§ 271(b) and/or (g) by making, having made, using, selling, offering for sale, and/or importing
`
`into the United States products that infringe the ’231 patent.
`
`
`
`10
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 11 of 32 PageID #: 11
`
`28.
`
`Based on the information presently available, Plaintiffs allege that NVIDIA’s
`
`40nm Fermi GPUs, 28nm Kepler GPUs, 28nm Maxwell GPUs, 16nm Pascal GPUs, 28nm Tegra
`
`K1 SoCs, and 20nm Tegra X1 SoCs are exemplary devices that infringe at least claim 1 of the
`
`’231 patent. The infringing products identified in this paragraph, all NVIDIA products that are
`
`substantially similar to these products, and products containing the same are referred to
`
`collectively as the “’231 Accused Products.” Plaintiffs make this preliminary identification of
`
`infringing products and infringed claims without the benefit of discovery or claim construction in
`
`this action, and expressly reserve the right to supplement and revise this identification of
`
`infringing products based on additional information obtained through discovery or otherwise.
`
`29.
`
`On information and belief, the ’231 Accused Products meet each and every
`
`limitation of at least claim 1 of the ’231 patent.
`
`30.
`
`Claim 1 of the ’231 patent recites a “method for providing a substantially planar
`
`semiconductor topography which extends above a plurality of electrically conductive features
`
`that form an integrated circuit[.]” On information and belief, the ’231 Accused Products
`
`comprise a substantially planar semiconductor topography that extends above a plurality of
`
`electrically conductive features that form an integrated circuit. For example, the ’231 Accused
`
`Products comprise a substantially planar layer extending over a layer below that contains a
`
`plurality of electrically conductive features that form an integrated circuit.
`
`31.
`
`Claim 1 of the ’231 patent requires “etching a plurality of laterally spaced dummy
`
`trenches into a dielectric layer between a first trench and a series of second trenches[.]” On
`
`information and belief, the ’231 Accused Products comprise semiconductor chips that are made
`
`by a process that includes etching a plurality of laterally spaced dummy trenches into a dielectric
`
`layer between a first trench and a series of second trenches. For example, the ’231 Accused
`
`
`
`11
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 12 of 32 PageID #: 12
`
`Products comprise multiple dummy trenches laterally spaced between a first interconnect and a
`
`series of second interconnects, each of which was formed in part by etching trenches into a layer
`
`of insulating material.
`
`32.
`
`Claim 1 of the ’231 patent further requires that “a lateral dimension of said first
`
`trench is greater than a lateral dimension of said second trenches[.]” On information and belief,
`
`the lateral dimension of a first trench is greater than a lateral dimension of a series of second
`
`trenches (i.e., the first trench is wider than at least one of the second trenches) in the ’231
`
`Accused Products. For example, the width of the first trench is greater than the width of one or
`
`more of the second trenches.
`
`33.
`
`Claim 1 of the ’231 patent further requires “filling said dummy trenches and said
`
`first and second trenches with a conductive material[.]” On information and belief, in the ’231
`
`Accused Products, the first, second, and dummy trenches are filled with a conductive material.
`
`For example, the first interconnect, second interconnects, and dummy connectors are formed
`
`from copper that was filled into trenches etched into the insulating layer.
`
`34.
`
`Claim 1 of the ’231 patent further requires “polishing said conductive material to
`
`form dummy conductors exclusively in said dummy trenches and interconnect exclusively in
`
`said first and second trenches[.]” On information and belief, in the ’231 Accused Products, the
`
`interconnects and dummy conductors are made by a process that includes polishing the
`
`conductive material deposited in the first, second, and dummy trenches until the conductive
`
`material is exclusively in those trenches (i.e., the conductive material in the first, second, and
`
`dummy trenches has been polished such that the copper in the dummy trenches does not connect
`
`to the copper in either of the first or second trenches). For example, copper deposited in the
`
`
`
`12
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 13 of 32 PageID #: 13
`
`dummy trenches has been polished so that it is separate from the copper deposited in the first and
`
`second trenches.
`
`35.
`
`Claim 1 of the ’231 patent further requires “said dummy conductors are
`
`electrically separate from said plurality of electrically conductive features and co-planar with
`
`said interconnect.” On information and belief, in the ’231 Accused Products, the dummy
`
`conductors are co-planar with the interconnect and electrically separate from the plurality of
`
`electrically conductive features. For example, the upper surfaces of the interconnects are
`
`coplanar with the upper surfaces of the dummy conductors, and the dummy conductors are
`
`electrically separate from the active or passive electrical components below the dummy
`
`conductors.
`
`36.
`
`NVIDIA has imported into the United States, or offered to sell, sell, or used
`
`within the United States, the ’231 Accused Products, knowing that such products are made by a
`
`process covered by at least claim 1 of the ’231 patent, in violation of 35 U.S.C. § 271(g). For
`
`example, NVIDIA has offered to sell the ’231 Accused Products in the United States through
`
`NVIDIA’s online store, https://web.archive.org/web/20150506105821/http://www.geforce.com/
`
`hardware (archived: May 6, 2015), and, on information and belief, through domestic retailers
`
`such as Best Buy. The infringing semiconductor chips of the ’231 Accused Products are neither
`
`materially changed by subsequent processes nor become trivial and nonessential components of
`
`another product.
`
`37.
`
`NVIDIA has actively, knowingly, and intentionally induced infringement of at
`
`least claim 1 of the ’231 patent in violation of 35 U.S.C. § 271(b). On information and belief,
`
`NVIDIA, knowing its products infringe the ’231 patent and with the specific intent for others to
`
`infringe the ’231 patent, has actively encouraged third parties, including OEMs, ODMs, system
`
`
`
`13
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 14 of 32 PageID #: 14
`
`builders, add-in board manufacturers (“AIBs”), automotive suppliers, and retailers/distributors,
`
`to sell, offer for sale, use, and/or import into the United States, without license or authority, ’231
`
`Accused Products and/or products containing ’231 Accused Products made by a process patented
`
`in the United States. For example, NVIDIA published and provided marketing materials,
`
`technical specifications, datasheets, user manuals, and development and testing resources on its
`
`website (http://www.nvidia.com/) that instructed and encouraged third parties to integrate the
`
`’231 Accused Products into products sold, offered for sale, used, and/or imported into the United
`
`States and encouraged NVIDIA’s customers to purchase and use those products in the United
`
`States. E.g., https://web.archive.org/web/20150506104826/http://www.geforce.com/hardware/
`
`compare-buy-gpus (archived: May 6, 2015); https://web.archive.org/web/20150821070328/
`
`http://www.nvidia.com/object/tegra.html (archived: August 21, 2015). NVIDIA has also
`
`established the “NVIDIA Partner Network” to assist customers with marketing, training, sales
`
`and distribution, and service and support. E.g., https://web.archive.org/web/20150819100649/
`
`http://www.nvidia.com/object/nvidia-partner-network.html (archived: August 19, 2015). These
`
`activities were designed to bring NVIDIA’s infringing products to market in the United States.
`
`38.
`
`Plaintiffs are entitled to recover from NVIDIA all damages that Plaintiffs have
`
`sustained as a result of NVIDIA’s infringement of the ’231 patent, including, without limitation,
`
`not less than a reasonable royalty.
`
`39.
`
`NVIDIA’s infringement of the ’231 patent has been willful and deliberate,
`
`entitling Plaintiffs to enhanced damages and attorneys’ fees.
`
`COUNT II
`INFRINGEMENT OF U.S. PATENT NO. 6,849,946
`
`40.
`
`Plaintiffs incorporate by reference the allegations set forth in paragraphs 1
`
`through 39 as though fully set forth herein.
`
`
`
`14
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 15 of 32 PageID #: 15
`
`41.
`
`On February 1, 2005, the USPTO duly and legally issued the ’946 patent, titled
`
`“Planarized Semiconductor Interconnect Topography and Method For Polishing a Metal Layer
`
`To Form Interconnect,” naming Anantha R. Sethuraman and Christopher A. Seams as inventors.
`
`A true and correct copy of the ’946 patent is attached hereto as Exhibit B.
`
`42.
`
`Invensas owns the entire right, title, and interest in and to the ’946 patent,
`
`including the right to sue and recover damages, including damages for past infringement.
`
`43.
`
`Plaintiffs have complied with applicable requirements of 35 U.S.C. § 287(a),
`
`which entitles Plaintiffs to receive damages for past infringement.
`
`44.
`
`By at least December 2, 2014, Plaintiffs disclosed the existence of the ’946 patent
`
`to NVIDIA and explained, in the form of claim charts, how certain exemplary NVIDIA devices
`
`infringe one or more claims of the ’946 patent. Thus, since at least December 2, 2014, NVIDIA
`
`has had knowledge of the ’946 patent and that its activities infringe the ’946 patent. In addition,
`
`since at least December 2, 2014, NVIDIA has known or should have known that its customers,
`
`distributors, and other purchasers of the ’946 Accused Products were infringing the ’946 patent.
`
`45.
`
`NVIDIA has infringed, directly and/or indirectly, either literally or under the
`
`doctrine of equivalents, at least claim 16 of the ’946 patent in violation of at least 35 U.S.C.
`
`§ 271(a) and/or (b) by making, having made, using, selling, offering for sale, and/or importing
`
`into the United States products that infringe the ’946 patent.
`
`46.
`
`Based on the information presently available to it, Plaintiffs allege that NVIDIA’s
`
`40nm Fermi GPUs, 28nm Kepler GPUs, 28nm Maxwell GPUs, 16nm Pascal GPUs, 28nm Tegra
`
`K1 SoCs, and 20nm Tegra X1 SoCs are exemplary devices that infringe at least claim 16 of the
`
`’946 patent. The infringing products identified in this paragraph, all NVIDIA products that are
`
`substantially similar to these products, and products containing the same are referred to
`
`
`
`15
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 16 of 32 PageID #: 16
`
`collectively as the “’946 Accused Products.” Plaintiffs make this preliminary identification of
`
`infringing products and infringed claims without the benefit of discovery or claim construction in
`
`this action, and expressly reserve the right to augment, supplement, and revise this identification
`
`of infringing products based on additional information obtained through discovery or otherwise.
`
`47.
`
`Claim 16 of the ’946 patent recites “[a] substantially planar semiconductor
`
`topography[.]” On information and belief, the ’946 Accused Products comprise a substantially
`
`planar semiconductor topography. For example, the upper surfaces of the first trench, plurality of
`
`laterally spaced dummy trenches, series of second trenches, and the dielectric layer are
`
`substantially planar.
`
`48.
`
`Claim 16 of the ’946 patent requires “a plurality of laterally spaced dummy
`
`trenches in a dielectric layer, between a first trench and a series of second trenches[.]” On
`
`information and belief, the ’946 Accused Products comprise a plurality of laterally spaced
`
`dummy trenches in a dielectric layer between a first trench and a series of second trenches. For
`
`example, there are multiple laterally spaced dummy trenches in insulating material that are
`
`between a first relatively wide trench and a series of second relatively narrow trenches.
`
`49.
`
`Claim 16 of the ’946 patent further requires that “each of the second trenches is
`
`relatively narrow compared to the first trench” and “a lateral dimension of at least one of the
`
`laterally spaced dummy trenches is less than a lateral dimension of the first trench and greater
`
`than a lateral dimension of at least one of the series of second trenches[.]” On information and
`
`belief, the second trenches in the ’946 Accused Products are relatively narrow compared to the
`
`first trench (i.e., each of the relatively narrow trenches is narrower than the relatively wide
`
`trench), and a lateral dimension of at least one of the laterally spaced dummy trenches is less
`
`than a lateral dimension of the first trench and greater than a lateral dimension of at least one of
`
`
`
`16
`
`

`

`Case 1:19-cv-00861-RGA Document 1 Filed 05/08/19 Page 17 of 32 PageID #: 17
`
`the series of second trenches. For example, the width of one or more of the dummy trenches is
`
`less than the width of the relatively wide trench, and greater than the width of one or more of the
`
`relatively narrow trenches.
`
`50.
`
`Claim 16 of the ’946 patent further requires “dummy conductors in said laterally
`
`spaced dummy trenches and electrically separate from electrically conductive features below
`
`said dummy conductors[.]” On information and belief, in the ’946 Accused Products, dummy
`
`conductors in the laterally spaced dummy trenches are electrically separate from electrically
`
`conductive features below the dummy conductors. For example