REDUNDANT COMPUTING ACROSS PLANES
Methods, systems, and devices for redundant computing across planes are described. A device may perform a computational operation on first data that is stored in a first plane that includes content-addressable memory cells. The first data may be representative of a set of contiguous bits of a vector. The device may perform, concurrent with performing the computational operation on the first data, the computational operation on second data that is stored in a second plane. The second data may be representative of the set of contiguous bits of the vector. The device may read from the first plane and write to the second plane, third data representative of a result of the computational operation on the first data.
1 . (canceled)
2 . An apparatus, comprising:
a memory die comprising a first plane and a second plane; and
logic coupled with the memory die and configured to:
perform, by the first plane based at least in part on a capability of content-addressable memory cells in the first plane, a computational operation on first data representative of a set of bits of a vector, wherein the computational operation is based at least in part on a first value, assigned to the first plane, for an arithmetic output bit;
perform, by the second plane concurrent with performing the computational operation on the first data and based at least in part on a capability of content-addressable memory cells in the second plane, the computational operation on second data representative of the set of bits of the vector, wherein the computational operation is based at least in part on a second value, assigned to the second plane, for the arithmetic output bit; and
copy, from the first plane and to the second plane based at least in part on the arithmetic output bit having the first value assigned to the first plane, third data representative of a result of the computational operation on the first data.
3 . The apparatus of claim 2 , wherein the set of bits comprises a first set of contiguous bits of the vector, and wherein the arithmetic output bit is based at least in part on a second set of contiguous bits of the vector, the second set of contiguous bits less significant than the first set of contiguous bits.
4 . The apparatus of claim 3 , wherein the logic is further configured to:
perform the computational operation on fourth data representative of the second set of contiguous bits; and
determine that the arithmetic output bit has the first value based at least in part on performing the computational operation on the fourth data.
5 . The apparatus of claim 4 , wherein the fourth data is stored in a third plane, and wherein the computational operation on the fourth data is performed concurrent with the computational operation on the first data and concurrent with concurrent with the computational operation on the second data.
6 . The apparatus of claim 2 , wherein the logic is further configured to:
write the third data to the first plane based at least in part on performing the computational operation on the first data; and
write, to the second plane, fourth data representative of a result of the computational operation on the second data, wherein writing the third data from the first plane to the second plane replaces the fourth data with the third data.
7 . The apparatus of claim 2 , wherein the logic is further configured to:
perform, concurrent with performing the computational operation on the first data and concurrent with performing the computational operation on the second data, the computational operation on fourth data that is stored in a third plane, wherein the fourth data is representative of a second set of bits of the vector more significant than the set of bits; and
perform, concurrent with performing the computational operation on the fourth data, the computational operation on fifth data that is stored in a fourth plane, wherein the fifth data is representative of the second set of bits of the vector.
8 . The apparatus of claim 7 , wherein the third plane is assigned the first value for a second arithmetic output bit, and wherein the fourth plane is assigned the second value for the second arithmetic output bit.
9 . The apparatus of claim 8 , wherein the logic is further configured to:
determine that the second arithmetic output bit has the first value; and
copy, from the third plane to the fourth plane based at least in part on the third plane being assigned the first value, sixth data representative of a result of the computational operation on the fourth data.
10 . A method, comprising:
performing, by a first plane of a memory die based at least in part on a capability of content-addressable memory cells in the first plane, a computational operation on first data representative of a set of bits of a vector, wherein the computational operation is based at least in part on a first value, assigned to the first plane, for an arithmetic output bit;
performing, by a second plane of the memory die concurrent with performing the computational operation on the first data and based at least in part on a capability of content-addressable memory cells in the second plane, the computational operation on second data representative of the set of bits of the vector, wherein the computational operation is based at least in part on a second value, assigned to the second plane, for the arithmetic output bit; and
copying, from the first plane and to the second plane based at least in part on the arithmetic output bit having the first value assigned to the first plane, third data representative of a result of the computational operation on the first data.
11 . The method of claim 10 , wherein the set of bits comprises a first set of contiguous bits of the vector, and wherein the arithmetic output bit is based at least in part on a second set of contiguous bits of the vector, the second set of contiguous bits less significant than the first set of contiguous bits.
12 . The method of claim 11 , further comprising:
performing the computational operation on fourth data representative of the second set of contiguous bits; and
determining that the arithmetic output bit has the first value based at least in part on performing the computational operation on the fourth data.
13 . The method of claim 12 , wherein the fourth data is stored in a third plane, and wherein the computational operation on the fourth data is performed concurrent with the computational operation on the first data and concurrent with concurrent with the computational operation on the second data.
14 . The method of claim 10 , further comprising:
writing the third data to the first plane based at least in part on performing the computational operation on the first data; and
writing, to the second plane, fourth data representative of a result of the computational operation on the second data, wherein writing the third data from the first plane to the second plane replaces the fourth data with the third data.
15 . The method of claim 10 , further comprising:
performing, concurrent with performing the computational operation on the first data and concurrent with performing the computational operation on the second data, the computational operation on fourth data that is stored in a third plane, wherein the fourth data is representative of a second set of bits of the vector more significant than the set of bits; and
performing, concurrent with performing the computational operation on the fourth data, the computational operation on fifth data that is stored in a fourth plane, wherein the fifth data is representative of the second set of bits of the vector.
16 . The method of claim 15 , wherein the third plane is assigned the first value for a second arithmetic output bit, and wherein the fourth plane is assigned the second value for the second arithmetic output bit.
17 . The method of claim 16 , further comprising:
determining that the second arithmetic output bit has the first value; and
copying, from the third plane to the fourth plane based at least in part on the third plane being assigned the first value, sixth data representative of a result of the computational operation on the fourth data.
18 . A non-transitory computer-readable medium storing code for operating a memory system, the code comprising instructions executable by one or more processors to cause the memory system to:
perform, by a first plane of a memory die based at least in part on a capability of content-addressable memory cells in the first plane, a computational operation on first data representative of a set of bits of a vector, wherein the computational operation is based at least in part on a first value, assigned to the first plane, for an arithmetic output bit;
perform, by a second plane of the memory die and concurrent with performing the computational operation on the first data and based at least in part on a capability of content-addressable memory cells in the second plane, the computational operation on second data representative of the set of bits of the vector, wherein the computational operation is based at least in part on a second value, assigned to the second plane, for the arithmetic output bit; and
copy, from the first plane and to the second plane based at least in part on the arithmetic output bit having the first value assigned to the first plane, third data representative of a result of the computational operation on the first data.
19 . The non-transitory computer-readable medium of claim 18 , wherein the set of bits comprises a first set of contiguous bits of the vector, and wherein the arithmetic output bit is based at least in part on a second set of contiguous bits of the vector, the second set of contiguous bits less significant than the first set of contiguous bits.
20 . The non-transitory computer-readable medium of claim 19 , wherein the instructions are further executable by the one or more processors to cause the memory system to:
perform the computational operation on fourth data representative of the second set of contiguous bits; and
determine that the arithmetic output bit has the first value based at least in part on performing the computational operation on the fourth data.
21 . The non-transitory computer-readable medium of claim 20 , wherein the fourth data is stored in a third plane, and wherein the computational operation on the fourth data is performed concurrent with the computational operation on the first data and concurrent with concurrent with the computational operation on the second data.