Abstract: Addition circuitry performs a saturating addition of a first number and a second number to generate a result value indicating an addition result corresponding to addition of the first number and the second number when the addition result is within a predetermined range and indicating a saturation value when the addition result is outside the predetermined range. The addition circuitry comprises: saturation lookahead circuitry to determine, for each lane of the result value, a respective set of one or more saturation lookahead status indications indicative of whether that lane should be set to represent part of the saturation value; and addition result generating circuitry to generate result bits for each lane, with a given lane of the result value having a value determined as a function of corresponding bits of the first and second numbers and a corresponding set of one or more saturation lookahead status indications determined for that lane by the saturation lookahead circuitry.

Abstract: There is provided an instruction, or instructions, that can be included in a program to perform a ray tracing operation, with individual execution threads in a group of execution threads executing the program performing the ray tracing operation for a respective ray in a corresponding group of rays such that the group of rays performing the ray tracing operation together. The instruction(s), when executed by the execution threads will cause one or more rays from the group of plural rays to be tested for intersection with a set of primitives. A result of the ray-primitive intersection testing can then be returned for the traversal operation.

Abstract: There is provided an instruction, or instructions, that can be included in a program to perform a ray tracing operation, with individual execution threads in a group of execution threads executing the program performing the ray tracing operation for a respective ray in a corresponding group of rays such that the group of rays performing the ray tracing operation together. The instruction(s), when executed by the execution threads will cause one or more rays from the group of plural rays to be tested for intersection with a set of primitives. A result of the ray-primitive intersection testing can then be returned for the traversal operation.

Abstract: A graphics processing apparatus comprises fragment generating circuitry to generate graphics fragments corresponding to graphics primitives, thread processing circuitry to perform threads of processing corresponding to the fragments, and forward kill circuitry to trigger a forward kill operation to prevent further processing of a target thread of processing corresponding to an earlier graphics fragment when the forward kill operation is enabled for the target thread and the earlier graphics fragment is determined to be obscured by one or more later graphics fragments. The thread processing circuitry supports enabling of the forward kill operation for a thread including at least one forward kill blocking instruction having a property indicative that the forward kill operation should be disabled for the given thread, when the thread processing circuitry has not yet reached a portion of the thread including the at least one forward kill blocking instruction.

Abstract: There is provided an apparatus and method for comparing wide data types. The apparatus comprises processing circuitry to perform a plurality of comparison operations in order to compare a first value and a second value, each of the first value and the second value having a length greater than N bits, and each comparison operation operating on a corresponding N bits of the first and second values. The plurality of comparison operations are chained to form a sequence such that each comparison operation is arranged to output an accumulated comparison result incorporating the comparison results of any previous comparison operations in the sequence, and such that for each comparison operation other than a final comparison operation in the sequence the accumulated comparison result is provided for use as an input by a next comparison operation in the sequence.

Abstract: An apparatus and method are provided for controlling rounding when performing a floating point operation. The apparatus has argument reduction circuitry to perform an argument reduction operation, and in addition provides reduce and round circuitry that generates from a supplied floating point value a modified floating point value to be input to the argument reduction circuitry. The reduce and round circuitry is arranged to modify a significand of the supplied floating point value, based on a specified value N, in order to produce a truncated significand with a specified rounding applied, the truncated significand being N bits shorter than the significand of the supplied floating point value, and then being used as a significand for the modified floating point value. The specified value N is chosen such that the argument reduction operation performed using the modified floating point value will inhibit roundoff error in a result of the argument reduction operation.

Abstract: Various encoding schemes are discussed for more efficiently encoding instructions which identify first and second architectural register numbers. In the first example, by constraining the first architectural register number to be greater than the second architectural register number, this frees up encodings for use in encoding other operations. In a second example, the first and second architectural register numbers may take any value but one of a first type of processing operation and a second type of processing operation is selected depending on a comparison of the first and second architectural register numbers.

Abstract: There is provided an apparatus and method for comparing wide data types. The apparatus comprises processing circuitry to perform a plurality of comparison operations in order to compare a first value and a second value, each of the first value and the second value having a length greater than N bits, and each comparison operation operating on a corresponding N bits of the first and second values. The plurality of comparison operations are chained to form a sequence such that each comparison operation is arranged to output an accumulated comparison result incorporating the comparison results of any previous comparison operations in the sequence, and such that for each comparison operation other than a final comparison operation in the sequence the accumulated comparison result is provided for use as an input by a next comparison operation in the sequence.

Abstract: A graphics processing apparatus comprises fragment generating circuitry to generate graphics fragments corresponding to graphics primitives, thread processing circuitry to perform threads of processing corresponding to the fragments, and forward kill circuitry to trigger a forward kill operation to prevent further processing of a target thread of processing corresponding to an earlier graphics fragment when the forward kill operation is enabled for the target thread and the earlier graphics fragment is determined to be obscured by one or more later graphics fragments. The thread processing circuitry supports enabling of the forward kill operation for a thread including at least one forward kill blocking instruction having a property indicative that the forward kill operation should be disabled for the given thread, when the thread processing circuitry has not yet reached a portion of the thread including the at least one forward kill blocking instruction.

Abstract: An apparatus and method are provided, the apparatus comprising: storage circuitry to store an input data value; divider circuitry to split the input data value into at least one sub-value in dependence on a number of lanes for a current iteration, each sub-value occupying a lane, and to operate on each sub-value to generate a quotient corresponding to the division of that sub-value by a divisor, wherein the divisor is an odd integer; remainder circuitry to operate on each sub-value to generate a remainder corresponding to the remainder of dividing that sub-value by the divisor; concatenation circuitry to concatenate each quotient to produce a concatenated division value, and to concatenate each remainder to produce a concatenated remainder value, in each subsequent iteration, the input data value being formed from the concatenated remainder value of a preceding iteration; and output circuitry to output, after a plurality of iterations, a result of adding the concatenated division values produced by said plura

Abstract: A graphics processing unit 3 includes a rasterizer 25, a thread spawner 40, a programmable execution unit 41, a varying interpolator 42, a texture mapper 43, and a blender 29. The programmable execution unit 41 is able to communicate with the varying interpolator 42, the texture mapper 43 and the blender 29 to request processing operations by those graphic specific accelerators. In addition to this, these graphics-specific accelerators are also able to communicate directly with each other and with the thread spawner 40, independently of the programmable execution unit 41. This allows for certain graphics processing operations to be performed using direct communication between the graphics-specific accelerators of the graphics processing unit, instead of executing instructions in the programmable execution unit to trigger the performance of those operations by the graphics-specific accelerators.

Abstract: An apparatus and method are provided for inhibiting roundoff error in a floating point argument reduction operation. The apparatus has reciprocal estimation circuitry that is responsive to a first floating point value to determine a second floating point value that is an estimated reciprocal of the first floating point value. During this determination, the second floating point value has both its magnitude and its error bound constrained in dependence on a specified value N. Argument reduction circuitry then performs an argument reduction operation using the first and second floating point values as inputs, in order to generate a third floating point value. The use of the specified value N to constrain both the magnitude and the error bound of the second floating point value causes roundoff error to be inhibited in the third floating point value that is generated by the argument reduction operation.

Abstract: In a compositing window system, as a respective version of the window for an application is written into a window buffer, a corresponding set of per tile signatures indicative of the content of each respective tile in the window buffer is generated and stored. When an updated version of the window is stored into a window buffer, the set of signature values for the updated version is compared to the set of signature values for the previous version in the window buffer to determine which tiles' content has changed. The set of tiles found to have changed is used to generate a set of regions for a window compositor to write to a window in a display frame buffer to update the window in the display frame buffer to display the new version of the window.

Abstract: An apparatus and method for generating a sum of floating-point input values are provided. To sum the values multiple partial sum floating-point values are maintained and the partial sum to which an input value may be added is selected by a least significant portion of the exponent of the input value. If the exponent of the input value is equal to the exponent of the value stored in the selected partial sum a mantissa sum of the input value and stored partial sum value replaces the mantissa value of the selected partial sum value. If the exponent of the input value is larger than the exponent of the value stored in the selected partial sum the selected partial sum value is replaced with the input value. An associative and deterministic summation is thus provided.

Abstract: A transaction elimination hardware unit controls the writing to a frame buffer in a memory of tiles generated by a tile-based graphics processor. The transaction elimination hardware unit has a signature generator that generates a signature representative of the content of the tile for each tile. A signature comparator then compares the signature of a new tile received from the graphics processor with the signatures of one or more tiles already stored in the frame buffer to see if the signatures match. If the signatures do not match, then the signature comparator controls a write controller to write the new tile to the frame buffer. On the other hand, if the signatures match, then no data is written to the frame buffer and the existing tile is allowed to remain in the frame buffer. In this way, a tile is only written to the frame buffer if it is found by the signature comparison to differ from the tile or tiles that are already stored in the frame buffer that it is compared with.

Abstract: Various encoding schemes are discussed for more efficiently encoding instructions which identify first and second architectural register numbers. In the first example, by constraining the first architectural register number to be greater than the second architectural register number, this frees up encodings for use in encoding other operations. In a second example, the first and second architectural register numbers may take any value but one of a first type of processing operation and a second type of processing operation is selected depending on a comparison of the first and second architectural register numbers.

Abstract: A graphics processing unit 3 includes a rasteriser 25, a thread spawner 40, a programmable execution unit 41, a varying interpolator 42, a texture mapper 43, and a blender 29. The programmable execution unit 41 is able to communicate with the varying interpolator 42, the texture mapper 43 and the blender 29 to request processing operations by those graphic specific accelerators. In addition to this, these graphics-specific accelerators are also able to communicate directly with each other and with the thread spawner 40, independently of the programmable execution unit 41. This allows for certain graphics processing operations to be performed using direct communication between the graphics-specific accelerators of the graphics processing unit, instead of executing instructions in the programmable execution unit to trigger the performance of those operations by the graphics-specific accelerators.

Abstract: An apparatus and method are provided for controlling rounding when performing a floating point operation. The apparatus has argument reduction circuitry to perform an argument reduction operation, and in addition provides reduce and round circuitry that generates from a supplied floating point value a modified floating point value to be input to the argument reduction circuitry. The reduce and round circuitry is arranged to modify a significand of the supplied floating point value, based on a specified value N, in order to produce a truncated significand with a specified rounding applied, the truncated significand being N bits shorter than the significand of the supplied floating point value, and then being used as a significand for the modified floating point value. The specified value N is chosen such that the argument reduction operation performed using the modified floating point value will inhibit roundoff error in a result of the argument reduction operation.

Abstract: An apparatus and method are provided, the apparatus comprising: storage circuitry to store an input data value; divider circuitry to split the input data value into at least one sub-value in dependence on a number of lanes for a current iteration, each sub-value occupying a lane, and to operate on each sub-value to generate a quotient corresponding to the division of that sub-value by a divisor, wherein the divisor is an odd integer; remainder circuitry to operate on each sub-value to generate a remainder corresponding to the remainder of dividing that sub-value by the divisor; concatenation circuitry to concatenate each quotient to produce a concatenated division value, and to concatenate each remainder to produce a concatenated remainder value, in each subsequent iteration, the input data value being formed from the concatenated remainder value of a preceding iteration; and output circuitry to output, after a plurality of iterations, a result of adding the concatenated division values produced by said plura

Abstract: Techniques for performing clipping of graphics primitives 60 with respect to a clipping boundary 65 are described. The clipping step 10 may be performed separately for each tile of a graphics frame to be rendered, after a primitive list for the tile has been read from a primitive memory 38. Clipping may be performed only for larger primitives whose size exceeds a given threshold. Clipping of a primitive 60 to the clipping boundary 65 may be performed inexactly so that only a single clipped primitive is generated which may extend beyond the clipping boundary. A clipped primitive generated by clipping may be used for a depth function calculation of a primitive setup operation and not for an edge determination.