{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

ptx_isa_1.1 - NVIDIA Compute PTX Parallel Thread Execution...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
ISA Version 1.1 10/24/2007 SP-03483-001_v1.1 NVIDIA Compute PTX: Parallel Thread Execution
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Background image of page 2
PTX ISA Version 1.1 i 10/24/2007 Document Change History Version Date Responsible Reason for Change _v1.0 June 15, 2007 RJ Preliminary release _v1.1 October 24, 2007 RJ, TS Release
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
ii PTX ISA Version 1.1 10/24/2007
Background image of page 4
PTX ISA Version 1.1 iii 10/24/2007 Table of Contents Chapter 1. Introduction ...................................................................................................... 1 1.1. Data-Parallel Computing Using GPUs ............................................................................. 1 1.2. Goals of PTX ................................................................................................................... 1 1.3. The Document’s Structure ............................................................................................... 2 Chapter 2. Programming Model ........................................................................................ 3 2.1. A Highly Multithreaded Coprocessor ............................................................................... 3 2.2. Thread Batching .............................................................................................................. 3 2.2.1. Cooperative Thread Arrays ..................................................................................... 3 2.2.2. Grid of Cooperative Thread Arrays .......................................................................... 4 Chapter 3. Parallel Thread Execution Machine Model ...................................................... 7 3.1. A Set of SIMD Multiprocessors with On-Chip Shared Memory ....................................... 7 3.2. Execution Model .............................................................................................................. 9 Chapter 4. Syntax ........................................................................................................... 11 4.1. Source Format ............................................................................................................... 11 4.2. Comments ..................................................................................................................... 11 4.3. Statements ..................................................................................................................... 12 4.3.1. Directive Statements .............................................................................................. 12 4.3.2. Instruction Statements ........................................................................................... 12 4.4. Identifiers ....................................................................................................................... 13 4.5. Immediate Constants ..................................................................................................... 14 4.5.1. Integer Immediate Constants ................................................................................ 14 4.5.2. Floating-point Immediate Constants ...................................................................... 14 4.5.3. Predicate Immediate Constants ............................................................................ 14 4.5.4. Constant Expressions ............................................................................................ 14 Chapter 5. State Spaces, Types, and Variables ............................................................. 15 5.1. State Spaces ................................................................................................................. 15 5.1.1. Register State Space ............................................................................................. 16 5.1.2. Special Register Space ......................................................................................... 16 5.1.3. Constant State Space ............................................................................................ 16 5.1.4. Global State Space ................................................................................................ 17 5.1.5. Local State Space .................................................................................................. 17
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
iv PTX ISA Version 1.1 10/24/2007 5.1.6. Parameter State Space ......................................................................................... 17 5.1.7. Shared State Space ............................................................................................... 17 5.1.8. Texture State Space .............................................................................................. 18 5.1.9. Surface State Space .............................................................................................. 18 5.2. Types ............................................................................................................................. 19 5.2.1. Fundamental Types ............................................................................................... 19 5.2.2. Restricted Use of Sub-word Sizes ......................................................................... 19 5.3. Variables ........................................................................................................................ 20 5.3.1. Variable Declarations ............................................................................................. 20 5.3.2. Vectors ................................................................................................................... 20 5.3.3. Array Declarations ................................................................................................. 21 5.3.4. Structures and Unions ........................................................................................... 21 5.3.5. Initializers ............................................................................................................... 22 5.3.6. Alignment ............................................................................................................... 22 Chapter 6. Instruction Operands ..................................................................................... 23 6.1. Operand Type Information ............................................................................................. 23 6.2. Source Operands ........................................................................................................... 23 6.3. Destination Operands .................................................................................................... 23 6.4. Using Addresses, Arrays, Vectors, Structures, and Unions .......................................... 24 6.4.1. Addresses as Operands ........................................................................................ 24 6.4.2. Arrays as Operands ............................................................................................... 25 6.4.3. Vectors as Operands ............................................................................................. 25 6.4.4. Structures and Unions as Operands ..................................................................... 26 6.4.5. Immediate Values as Operands ............................................................................ 26 6.5. Type Conversion ............................................................................................................ 26 6.5.1. Scalar Conversions ................................................................................................ 26 6.5.2. Rounding Modes .................................................................................................... 28 6.5.3. Vector Conversions ............................................................................................... 29 6.6. Operand Costs ............................................................................................................... 30 Chapter 7. Instruction Set ............................................................................................... 31 7.1. Format and Semantics of Instruction Descriptions ........................................................ 31 7.2. PTX Instructions ............................................................................................................ 31 7.3. Predicated Execution ..................................................................................................... 32 7.3.1. Comparisons .......................................................................................................... 33 7.3.1.1. Integer and Bit-Size Comparisons ................................................................. 33
Background image of page 6
PTX ISA Version 1.1 v 10/24/2007 7.3.1.2. Floating-point Comparisons ........................................................................... 33 7.3.2. Manipulating Predicates ........................................................................................ 34 7.4. Type Information for Instructions and Operands ........................................................... 35 7.5. Divergence of Threads in Control Constructs ............................................................... 35 7.6. Semantics ...................................................................................................................... 36 7.6.1. Machine-specific Semantics of 16-bit Code .......................................................... 36 7.7. Instructions .................................................................................................................... 37 7.7.1. Arithmetic Instructions ........................................................................................... 37 7.7.2. Comparison and Selection Instructions ................................................................. 45 7.7.3. Logic and Shift Instructions ................................................................................... 49 7.7.4. Data Movement and Conversion Instructions ........................................................ 52 7.7.5. Texture Instruction ................................................................................................. 56 7.7.6. Control Flow Instructions ....................................................................................... 57 7.7.7. Parallel Synchronization and Communication Instructions ................................... 60 7.7.8. Floating-point Instructions ...................................................................................... 62 7.7.9. Miscellaneous Instructions .................................................................................... 65 Chapter 8. Special Registers .......................................................................................... 67 Chapter 9. Directives ....................................................................................................... 71 9.1. Specifying CTAs and Functions .................................................................................... 71 9.2. Debugging Directives ..................................................................................................... 73 9.3. Other Directives ............................................................................................................. 74 Chapter 10. Release Notes ............................................................................................. 77 10.1. New Features ............................................................................................................ 77 10.2. Unimplemented Features Removed From ISA ......................................................... 77 10.3.
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}