What is claimed is:
1. A reflective display device comprising:
a panel comprising a transparent first substrate lying on the side of external incident light, a second substrate joined to said first substrate with a predetermined gap therebetween and lying on the reflection side, an electro-optical material held in said gap, and an electrode provided on at least one of said first substrate and said second substrate for applying a voltage to said electro-optical material;
a light guide plate arranged on the outside of said first substrate, said light guide plate normally transmitting the external light onto said first substrate and emitting the external light reflected from said second substrate, while, as required, guiding illumination light onto said first substrate and emitting the illumination light reflected from said second substrate; and
a light source arranged on the end of said light guide plate.
2. A reflective display device according to claim 1, wherein said light guide plate and said panel are joined to each other with a transparent intervening layer therebetween and a refractive index of said intervening layer is appropriately set so as to suppress undesirable reflection of the illumination light and the external light at the interface between said light guide plate and said panel.
3. A reflective display device according to claim 1, wherein said intervening layer comprises a transparent resin having adhesion.
4. A reflective display device according to claim 3, wherein said light guide plate is provided with a groove on the back surface thereof for preventing said resin from leaking out when the back surface of said light guide plate and the surface of said panel are joined to each other.
5. A reflective display device according to claim 1, wherein said reflective display device further comprises a collimating means for collimating the illumination light radiating from said light source and leading it perpendicularly onto the end of said light guide plate.
6. A reflective display device according to claim 5, wherein said light source is semicylindrically formed and arranged facing the end of said light guide plate and said collimating means corresponds to a semicylindrical collimator lens arranged between said light source and said light guide plate.
7. A reflective display device according to claim 1, wherein a polarizing plate is provided between said light source and said light guide plate for converting the unpolarized illumination light radiating from said light source into linearly polarized light, leading it onto said light guide plate, and suppressing undesirable scattering of the illumination light inside said light guide plate.
8. A reflective display device according to claim 7, wherein said polarizing plate converts illumination light into linearly polarized light which is parallel to or perpendicular to said light guide plate.
9. A reflective display device according to claim 7, wherein said electro-optical material comprises a liquid crystal which can be controlled in the alignment direction parallel to or orthogonally to the polarization direction of said illumination light converted into linearly polarized light.
10. A reflective display device according to claim 1, wherein said light guide plate comprises a planar section divided into bands and an inclined step lying between each band of said planar section and said light guide plate reflects the illumination light guided forward at each step so as to guide it onto said first substrate and also emits the illumination light reflected from said second substrate through said planar section.
11. A reflective display device according to claim 10, wherein said step of said light guide plate inclines in the range from 40 to 50 degrees toward said planar section.
12. A reflective display device according to claim 10, wherein said step comprises a curved inclined area for reflecting illumination light diffusively so as to lead it onto said first substrate.
13. A reflective display device according to claim 10, wherein each said step is formed so as to have a different angle of inclination for reflecting illumination light in accordance with the angle of inclination and leading it onto said first substrate at a different angle.
14. A reflective display device according to claim 1, wherein said light guide plate comprises a trapezoidal section divided into bands and an inclined step lying between each band of said trapezoidal section, each band of said trapezoidal section comprising a curved lens area, and said light guide plate reflects the illumination light radiating from said light source at each step so as to guide it onto said first substrate and emits the illumination light reflected from said second substrate through said lens area of each band of said trapezoidal section.
15. A reflective display device according to claim 1, wherein said panel comprises a guest-host liquid crystal layer as said electro-optical material, comprising a liquid crystal as a host to which a dichroic dye is added as a guest.
16. A reflective display device according to claim 15, wherein said panel comprises a reflecting layer lying on the side of said second substrate for scattering and reflecting external light, and a quarter-wavelength layer provided between said guest-host liquid crystal layer and said reflecting layer.
17. A reflective display device according to claim 1, wherein said panel comprises a polarizing plate provided on the side of said first substrate and a liquid crystal layer as said electro-optical material, said liquid crystal layer functioning as a quarter-wavelength plate in response to the state of an applied voltage.
18. A reflective display device according to claim 17, wherein a quarter-wavelength plate is provided between said polarizing plate and said liquid crystal layer, and said liquid crystal layer comprises a nematic liquid crystal layer having a positive dielectric anisotropy and a twisted alignment, functions as a quarter-wavelength plate in the absence of an applied voltage, and does not function as a quarter-wavelength plate in the presence of an applied voltage.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method in a data processing system for determining the memory request load placed on one of a plurality of physically separate memory banks by a plurality of processors, said plurality of memory banks and said plurality of processors being physically distributed throughout a semiconductor substrate in said data processing system, said method comprising the steps of:
one of said plurality of processors being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for said one of said plurality of processors to access said one of said plurality of memory banks being different from an access time for said one of said plurality of processors to access said others of said plurality of memory banks;
determining a relative size of one of said plurality of memory banks with respect to a total size of all of said plurality of memory banks; and
estimating a load placed on said one of said plurality of memory banks by determining a number of said plurality of processors that have all of their memory requests satisfied by said one of said plurality of memory banks utilizing said determined relative size and a value of a total quantity of said plurality of processors.
2. The method according to claim 1, further comprising:
grouping said plurality of processors in physically separate clusters;
each processor within a cluster having the same access time for accessing one of said plurality of memory banks; and
distributing said clusters throughout said semiconductor substrate, one of said clusters being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for any processor included in said one of said clusters to access said one of said plurality of memory banks being different from an access time for any processor included in said one of said clusters to access said others of said plurality of memory banks.
3. The method according to claim 2, further comprising:
satisfying a memory request by one of said processors included in said one of said clusters utilizing one of said others of said plurality of memory banks that is not physically closest to said one of said clusters.
4. The method according to claim 1, further comprising the steps of:
determining a relative size of said one of said plurality of memory banks with respect to a total size of all of said plurality of memory banks; and
estimating said number of said plurality of processors that have all of their memory requests satisfied by said one of said plurality of memory banks by multiplying said determined relative size of said one of said plurality of memory banks times a value that is equal to a total number of said plurality of processor.
5. A method in a data processing system for determining the memory request load placed on one of a plurality of memory requests by a plurality of processors, said plurality of memory banks and said plurality of processors physically distributed throughout a semiconductor substrate included in said data processing system, said method comprising the steps of:
one of said plurality of processors being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for said one of said plurality of processors to access said one of said plurality of memory banks being different from an access time for said one of said plurality of processors to access said others of said plurality of memory banks;
estimating a load placed on said one of said plurality of memory banks by estimating, for each one of said plurality of processors, a fraction of memory requests made by each one of said plurality of processors to said one of said plurality of memory banks; and
estimating a total load placed on said one of said plurality of memory banks utilizing said estimation of said load placed on said one of said plurality of memory banks by each one of said plurality of processors.
6. The method according to claim 5, further comprising:
grouping said plurality of processors in physically separate clusters;
each processor within a cluster having the same access time for accessing one of said plurality of memory banks; and
distributing said clusters throughout said semiconductor substrate, one of said clusters being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for any processor included in said one of said clusters to access said one of said plurality of memory banks being different from an access time for any processor included in said one of said clusters to access said others of said plurality of memory banks.
7. The method according to claim 6, further comprising:
satisfying a memory request by one of said processors included in said one of said clusters utilizing one of said others of said plurality of memory banks that is not physically closest to said one of said clusters.
8. The method according to claim 5, further comprising the steps of:
estimating a total load placed on said one of said plurality of memory banks by all of said plurality of processors by generating a sum of each estimated fraction of memory requests made by each one of said plurality of processors to said one of said plurality of memory banks.
9. A data processing system for determining the memory request load placed on one of a plurality of physically separate memory banks by a plurality of processors, said plurality of memory banks and said plurality of processors being physically distributed throughout a semiconductor substrate in said data processing system, said system comprising:
one of said plurality of processors being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, access time for said one of said plurality of processors to access said one of said plurality of memory banks being different from an access time for said one of said plurality of processors to access said others of said plurality of memory banks;
determining means for determining a relative size of one of said plurality of memory banks with respect to a total size of all of said plurality of memory banks; and
estimating means for estimating a load placed on said one of said plurality of memory banks by determining a number of plurality of processors that have all of their memory requests satisfied by said one of said plurality of memory banks utilizing said determined relative size and a value of a total quantity of said plurality of processors.
10. The system according to claim 9, further comprising:
said plurality of processors grouped in physically separate clusters;
each processor within a cluster having the same access time for accessing one of said plurality of memory banks; and
said clusters distributed throughout said semiconductor substrate, one of said clusters being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for any processor included in said one of said clusters to access said one of said plurality of memory banks being different from an access time for any processor included in said one of said clusters to access said others of said plurality of memory banks.
11. The system according to claim 10,
a memory request by one of said processors included in said one of said clusters being satisfied utilizing one of said others of said plurality of memory banks that is not physically closest to said one of said clusters.
12. The system according to claim 9, further comprising:
determining means for determining a relative size of said one of said plurality of memory banks with respect to a total size of all of said plurality of memory banks; and
estimating means for estimating said number of said plurality of processors that have all of their memory requests satisfied by said one of said plurality of memory banks by multiplying said determined relative size of said one of said plurality of memory banks times a value that is equal to a total number of said plurality of processors.
13. A data processing system for determining the memory request load placed on one of a plurality of memory banks by a plurality of processors, said plurality of memory banks and said plurality of processors physically distributed throughout a semiconductor substrate included in said data processing system, said system comprising:
one of said plurality of processors being located physically closer to one of said plurality of memory bank than to others of said plurality of memory banks, an access time for said one of said plurality of processors to access said one of said plurality of memory banks being different from an access time for said one of said plurality of processors to access said others of said plurality of memory banks;
estimating means for estimating a load placed on said one of said plurality of memory banks by estimating, for each of said plurality of processors, a fraction of total memory requests made by each one of said plurality of processors to said one of said plurality of memory banks; and
estimating means for estimating a total load placed on said one of said plurality of memory banks utilizing said estimation of said load placed on said one of said plurality of memory banks by each one of said plurality of processors.
14. The system according to claim 13, further comprising:
said plurality of processors grouped in physically separate clusters;
each processor within a cluster having the same access time for accessing one of said plurality of memory banks; and
said clusters distributed throughout said semiconductor substrate, one of said clusters being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for any processor included in said one of said clusters to access said one of said plurality of memory banks being different from an access time for any processor included in said one of said clusters to access said others of said plurality of memory banks.
15. The system according to claim 14, further comprising:
a memory request by one of said processors included in said one of said clusters being satisfied utilizing one of said others of said plurality of memory banks that is not physically closest to said one of said clusters.
16. The system according to claim 13, further comprising:
estimating means for estimating a total load placed on said one of said plurality of memory banks by all of said plurality of processors by generating a sum of each estimated fraction of memory requests made by each one of said plurality of processors to said one of said plurality of memory banks.
17. A computer program product in a data processing system for determining the memory request load placed on one of a plurality of memory banks by a plurality of processors, said plurality of memory banks and said plurality of processors physically distributed throughout a semiconductor substrate in said data processing system, said product comprising:
one of said plurality of processors being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for said one of said plurality of processors to access said one of said plurality of memory banks being different from an access time for said one of said plurality of processors to access said others of said plurality of memory banks;
instruction means for determining a relative size of one of said plurality of memory banks with respect to a total size of all of said plurality of memory banks; and
instruction means for estimating a load placed on said one of said plurality of memory banks by determining a number of said plurality of processors that have all of their memory request satisfied by said one of said plurality of memory banks utilizing said determined relative size and a value of a total quantity of said plurality of processors.
18. The product according to claim 17, further comprising:
grouping said plurality of processors in physically separate clusters;
each processor within a cluster having the same access time for accessing one of said plurality of memory banks;
distributing said clusters throughout said semiconductor substrate, one of said clusters being located physically closer to one of said plurality of memory banks than to others of said plurality of memory banks, an access time for any processor included in said one of said clusters to access said one of said plurality of memory banks being different from an access time for any processor included in said one of said clusters to access said others of said plurality of memory banks; and
instructions for satisfying a memory request by one of said processors included in said one of said clusters utilizing one of said others of said plurality of memory banks that is not physically closest to said one of said clusters.
19. The product according to claim 17, further comprising:
instruction means for determining a relative size of said one of said plurality of memory banks with respect to a total size of all of said plurality of memory banks; and
instruction means for estimating said number of said plurality of processors that have all of their memory requests satisfied by said one of said plurality of memory banks by multiplying said determined relative size of said one of said plurality of memory banks times a value that is equal to a total number of said plurality of processors.