Implementation av flyttalsaritmetik i FPGA 1999 (Svenska)Självständigt arbete på grundnivå (kandidatexamen)Studentuppsats (Examensarbete)

Abstract [sv]

Todays new FPGAs are larger, faster and more efficient then past generations. FPGA is nowadays a suitable choice for construction implementation, instead of full custom design ASICs. It is relevant to see what FPGA can do with DSP (Digital Signal Processing). Binary fixed point arithmetic have until this stage, been the most common numeric presentation in DSP. Floating point presentation have lately been more used, why there are no facts showing how good performance the FPGA, can calculate floating point arithmetic. Furthermore it is objective to see how large the floating point implementation will be compared to fixed point arithmetic. The purpose of the project is to examine area and speed for applications with both fixed point and floating point arithmetic, implemented in Xilinx FPGAs. The fundamental arithmetic functions are addition, subtraction and multiplication. This report shows a comparison between fixed point and floating point arithmetic, implemented in Xilinx XC40150XV. The binary floating point presentation is 32 bits according to IEEE 754 standard.

Ort, förlag, år, upplaga, sidor

1999.

Nyckelord [sv]

FPGA, Xilinx, XC40150XV, Construction, IEEE 754, Implementation, DSP, Signal, Floating, Fix, Point, Area, Speed, Addition, Subtraction, Multiplication

Identifikatorer

URN: urn:nbn:se:hh:diva-8258Lokalt ID: U2212OAI: oai:DiVA.org:hh-8258DiVA, id: diva2:363343

Uppsök

teknik

Anmärkning

Denna uppsats kan beställas från arkivet / This paper can be ordered from the archive. Kontakta / Contact: arkivet@hh.seTillgänglig från: 2010-11-09 Skapad: 2010-11-09 Senast uppdaterad: 2025-10-01Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Av organisationen

Sektionen för ekonomi och teknik (SET)

Sök vidare utanför DiVA

GoogleGoogle ScholarTotalt: 108 träffar