GPU-based advanced memory diagnostics over dynamic memory regions for faster and efficient diagnostics
An information handling system may include a central processing unit (CPU), a graphics processing unit (GPU) including a plurality of processing cores, a memory coupled to the CPU and to the GPU, and a basic input/output system (BIOS). While the information handling system is in a pre-boot environment and prior to initialization of an operating system of the information handling system, the BIOS may cause the central processing unit to select respective portions of the memory for failure testing; and cause individual ones of the plurality of processing cores of the GPU to carry out the failure testing of the respective portions of the memory.
1. An information handling system comprising:
a central processing unit (CPU);
a graphics processing unit (GPU) comprising a plurality of processing cores;
a memory coupled to the CPU and to the GPU; and
a basic input/output system (BIOS) configured to, while the information handling system is in a pre-boot environment and prior to initialization of an operating system of the information handling system:
cause the CPU to select respective portions of the memory for failure testing; and
cause individual ones of the plurality of processing cores of the GPU to carry out the failure testing of the respective portions of the memory;
wherein, during each particular boot of a plurality of boots of the information handling system, the failure testing is carried out on only a particular subset of the memory, and wherein the respective portions of the memory are selected such that, over the plurality of boots of the information handling system, the failure testing is carried out on an entirety of the memory.
2. The information handling system of claim 1 , wherein the BIOS is a Unified Extensible Firmware Interface (UEFI) BIOS.
3. The information handling system of claim 1 , wherein the BIOS is further configured to:
detect a particular portion of the memory that has failed; and
mark the particular portion of the memory such that the operating system is configured to initialize without using the particular portion of the memory.
4. The information handling system of claim 3 , wherein the initialization of the operating system is configured to occur without an additional reboot of the information handling system.
5. The information handling system of claim 1 , wherein the individual ones of the plurality of processing cores of the GPU are configured to carry out the failure testing of the respective portions of the memory concurrently.
6. The information handling system of claim 1 , wherein the selection of the respective portions of the memory for failure testing is based at least in part on usage statistics for the memory.
7. The information handling system of claim 1 , wherein the selection of the respective portions of the memory for failure testing is based at least in part on statistics for prior failure tests of the memory.
8. The information handling system of claim 1 , wherein the BIOS is configured to carry out the selecting and the failure testing on every boot of the information handling system.
9. A method comprising:
while an information handling system is in a pre-boot environment and prior to initialization of an operating system of the information handling system:
a basic input/output system (BIOS) of the information handling system causing a central processing unit (CPU) of the information handling system to select respective portions of a memory for failure testing; and
the BIOS causing individual ones of a plurality of processing cores of a graphics processing unit (GPU) of the information handling system to carry out the failure testing of the respective portions of the memory;
wherein, during each particular boot of a plurality of boots of the information handling system, the failure testing is carried out on only a particular subset of the memory, and wherein the respective portions of the memory are selected such that, over the plurality of boots of the information handling system, the failure testing is carried out on an entirety of the memory.
10. The method of claim 9 , wherein the memory is random access memory (RAM).
11. The method of claim 9 , wherein the CPU includes a plurality of cores, and wherein the selecting is carried out by a single one of the plurality of cores of the CPU.
12. The method of claim 9 , wherein the selection of the respective portions of the memory for failure testing is based on usage statistics for the memory and on statistics for prior failure tests of the memory.
13. An article of manufacture comprising a non-transitory, computer-readable medium having computer-executable code thereon that is executable by an information handling system for, while the information handling system is in a pre-boot environment and prior to initialization of an operating system of the information handling system:
a basic input/output system (BIOS) of the information handling system causing a central processing unit (CPU) of the information handling system to select respective portions of a memory for failure testing; and
the BIOS causing individual ones of a plurality of processing cores of a graphics processing unit (GPU) of the information handling system to carry out the failure testing of the respective portions of the memory;
wherein, during each particular boot of a plurality of boots of the information handling system, the failure testing is carried out on only a particular subset of the memory, and wherein the respective portions of the memory are selected such that, over the plurality of boots of the information handling system, the failure testing is carried out on an entirety of the memory.
14. The article of claim 13 , wherein the BIOS is a Unified Extensible Firmware Interface (UEFI) BIOS.
15. The article of claim 13 , wherein the code is further for:
detecting a particular portion of the memory that has failed; and
marking the particular portion of the memory such that the operating system is configured to initialize without using the particular portion of the memory.
16. The article of claim 15 , wherein the initialization of the operating system is configured to occur without an additional reboot of the information handling system.
17. The article of claim 13 , wherein the individual ones of the plurality of processing cores of the GPU are configured to carry out the failure testing of the respective portions of the memory concurrently.
18. The article of claim 13 , wherein the selection of the respective portions of the memory for failure testing is based at least in part on usage statistics for the memory.
19. The article of claim 13 , wherein the selection of the respective portions of the memory for failure testing is based at least in part on statistics for prior failure tests of the memory.
20. The article of claim 13 , wherein the code is further for carrying out the selecting and the failure testing on every boot of the information handling system.