Coalescing adjacent gather/scatter operations

Patent metadata

Field	Value
Publication number	US-9612842-B2
Application number	US-201514976231-A
Country	US
Kind code	B2
Filing date	Dec 21, 2015
Priority date	Dec 26, 2012
Publication date	Apr 4, 2017
Grant date	Apr 4, 2017

Abstract

According to one embodiment, a processor includes an instruction decoder to decode a first instruction to gather data elements from memory, the first instruction having a first operand specifying a first storage location and a second operand specifying a first memory address storing a plurality of data elements. The processor further includes an execution unit coupled to the instruction decoder, in response to the first instruction, to read contiguous a first and a second of the data elements from a memory location based on the first memory address indicated by the second operand, and to store the first data element in a first entry of the first storage location and a second data element in a second entry of a second storage location corresponding to the first entry of the first storage location.

First claim

What is claimed is:

1. A server comprising:
a Peripheral Component Interconnect Express (PCIe) interface of the server; and
a processor of the server, the processor comprising:
a plurality of 64-bit general-purpose registers;
a plurality of 128-bit single instruction, multiple data (SIMD) registers;
a data cache to cache data;
an instruction cache to cache instructions;
an instruction fetch unit coupled to the instruction cache to fetch the instructions;
a decode unit coupled to the instruction fetch unit, the decode unit to decode the instructions, including a first instruction, the first instruction to indicate a 128-bit operand size, the first instruction having a first field to specify a first 128-bit SIMD destination register of the plurality of 128-bit SIMD registers, the first instruction having a second field to specify a 64-bit general-purpose register of the plurality of 64-bit general-purpose registers to store a base address, and the first instruction to indicate a data element width of 64-bits; and
an execution unit coupled to the decode unit, coupled to the plurality of 128-bit SIMD registers, and coupled to the plurality of 64-bit general-purpose registers, the execution unit to execute the first instruction to:
load a first structure and a second structure from a memory based on the base address, the first structure to include a first 64-bit data element, a second 64-bit data element, and a third 64-bit data element, the second structure to include a first 64-bit data element, a second 64-bit data element, and a third 64-bit data element, wherein the first 64-bit data element, the second 64-bit data element, and the third 64-bit data element of the first structure are to be consecutive elements in the memory, and wherein the first 64-bit data element, the second 64-bit data element, and the third 64-bit data element of the second structure are to be consecutive elements in the memory; and
store the first 64-bit data element of the first structure as a first 64-bit data element of the first 128-bit SIMD destination register, the second 64-bit data element of the first structure as a first 64-bit data element of a second 128-bit SIMD destination register, the third 64-bit data element of the first structure as a first 64-bit data element of a third 128-bit SIMD destination register, the first 64-bit data element of the second structure as a second 64-bit data element of the first 128-bit SIMD destination register, the second 64-bit data element of the second structure as a second 64-bit data element of the second 128-bit SIMD destination register, and the third 64-bit data element of the second structure as a second 64-bit data element of the third 128-bit SIMD destination register, wherein the first 64-bit data element of the first 128-bit SIMD destination register is to include least significant bits of the first 128-bit SIMD destination register, wherein the first 64-bit data element of the second 128-bit SIMD destination register is to include least significant bits of the second 128-bit SIMD destination register, and wherein the first 64-bit data element of the third 128-bit SIMD destination register is to include least significant bits of the third 128-bit SIMD destination register.

2. The server of claim 1 , wherein the first instruction has a data element width field to indicate the data element width of 64-bits.

3. The server of claim 1 , wherein a single bit of the first instruction is to indicate the 128-bit operand size.

4. The server of claim 1 , wherein the first, second, and third 128-bit SIMD source registers are a sequence of registers.

5. The server of claim 1 , wherein the processor has a reduced instruction set computing (RISC) architecture.

6. The server of claim 1 , wherein the processor is coupled to a coprocessor, wherein the coprocessor is a network processor.

7. The server of claim 1 , wherein the processor comprises a memory controller.

8. The server of claim 1 , further comprising data storage.

9. The server of claim 1 , further comprising memory.

10. The server of claim 1 , further comprising one or more I/O devices.

11. The server of claim 1 , further comprising a power control unit.

12. The server of claim 1 , further comprising a device to communicate with one or more other electronic devices over a network.

13. A server comprising:
a Peripheral Component Interconnect Express (PCIe) interface of the server;
memory;
data storage; and
a processor of the server, the processor coupled with the data storage and comprising:
a plurality of 64-bit general-purpose registers;
a plurality of 128-bit single instruction, multiple data (SIMD) registers;
a data cache to cache data;
an instruction cache to cache instructions;
an instruction fetch unit coupled to the instruction cache to fetch the instructions;
a decode unit coupled to the instruction fetch unit, the decode unit to decode the instructions, including a first instruction, the first instruction to indicate a 128-bit operand size, the first instruction having a first field to specify a first 128-bit SIMD destination register of the plurality of 128-bit SIMD registers, the first instruction having a second field to specify a 64-bit general-purpose register of the plurality of 64-bit general-purpose registers to store a base address, and the first instruction to indicate a data element width of 64-bits; and
an execution unit coupled to the decode unit, coupled to the plurality of 128-bit SIMD registers, and coupled to the plurality of 64-bit general-purpose registers, the execution unit to execute the first instruction to:
load a first structure and a second structure from a memory based on the base address, the first structure to include a first 64-bit data element, a second 64-bit data element, and a third 64-bit data element, the second structure to include a first 64-bit data element, a second 64-bit data element, and a third 64-bit data element, wherein the first 64-bit data element, the second 64-bit data element, and the third 64-bit data element of the first structure are to be consecutive elements in the memory, and wherein the first 64-bit data element, the second 64-bit data element, and the third 64-bit data element of the second structure are to be consecutive elements in the memory; and
store the first 64-bit data element of the first structure as a first 64-bit data element of the first 128-bit SIMD destination register, the second 64-bit data element of the first structure as a first 64-bit data element of a second 128-bit SIMD destination register, the third 64-bit data element of the first structure as a first 64-bit data element of a third 128-bit SIMD destination register, the first 64-bit data element of the second structure as a second 64-bit data element of the first 128-bit SIMD destination register, the second 64-bit data element of the second structure as a second 64-bit data element of the second 128-bit SIMD destination register, and the third 64-bit data element of the second structure as a second 64-bit data element of the third 128-bit SIMD destination register, wherein the first 64-bit data element of the first 128-bit SIMD destination register is to include least significant bits of the first 128-bit SIMD destination register, wherein the first 64-bit data element of the second 128-bit SIMD destination register is to include least significant bits of the second 128-bit SIMD destination register, and wherein the first 64-bit data element of the third 128-bit SIMD destination register is to include least significant bits of the third 128-bit SIMD destination register.

14. The server of claim 13 , wh

Assignees

• Intel Corp

Inventors

• Forsyth Andrew T
• Hickmann Brian J
• Hall Jonathan C
• Hughes Christopher J

Classifications

• G06F9/30181

  Instruction operation extension or modification · CPC title

• G06F13/4282

  on a serial bus, e.g. I2C bus, SPI bus (on daisy chain buses G06F13/4247) · CPC title

• G06F9/3836

  Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution · CPC title

• G06F2212/68

  Details of translation look-aside buffer [TLB] · CPC title

• G06F9/30098

  Register arrangements · CPC title