Files
blis/bench/bench_aocl_gemm/bench_batch_input.txt
Meghana Vankadari 852cdc6a9a Implemented batch_matmul for f32 & int8 datatypes
Details:
- The batch matmul performs a series of matmuls, processing
  more than one GEMM problem at once.
- Introduced a new parameter called batch_size for the user
  to indicate number of GEMM problems in a batch/group.
- This operation supports processing GEMM problems with
  different parameters including dims,post-ops,stor-schemes etc.,
- This operation is optimized for problems where all the
  GEMMs in a batch are of same size and shape.
- For now, the threads are distributed among different GEMM
  problems equally irrespective of their dimensions which
  leads to better performance for batches with identical GEMMs
  but performs sub-optimally for batches with non-identical GEMMs.
- Optimizations for batches with non-identical GEMMs is in progress.
- Added bench and input files for batch_matmul.
- Added logger functionality for batch_matmul APIs.

AMD-Internal: [SWLCSG-2944]
Change-Id: I83e26c1f30a5dd5a31139f6706ac74be0aa6bd9a
2025-01-10 04:10:53 -05:00

18 lines
950 B
Plaintext

*:bs=5
r t t n n 92 1479 589 92 589 1479 scale=vector,zp=vector,bias=na,clip
r n n n r 67 21 1823 1823 21 21 scale=vector,zp=scalar,relu,clip
r n t n n 43 2240 1553 1553 1553 2240 scale=vector,zp=scalar,relu,clip
r t n n p 143 1943 730 143 1943 1943 bias=na,swish
r n n n r 79 2676 1995 1995 2676 2676 bias=na,swish
bf16s4f32of32:bs=4
r t n n r 43 1110 271 43 1110 1110 scale=vector,zp=vector,bias=na,clip
r t n n r 79 1177 1968 79 1177 1177 scale=vector,zp=scalar,relu,clip
r n t n r 92 2872 1482 1482 1482 2872 scale=vector,zp=vector,bias=na,clip
r n t n r 88 3397 1130 1130 1130 3397 scale=vector,zp=vector
bf16s4f32obf16:bs=5
r n n n r 17 2714 468 468 2714 2714 scale=vector,zp=vector,bias=na,clip
r n n n r 140 3764 1519 1519 3764 3764 scale=vector,zp=vector
r n t n r 17 1758 1034 1034 1034 1758 scale=vector,zp=vector,bias=na,clip
r n n n r 130 1822 1293 1293 1822 1822 scale=vector,zp=vector
r t t n r 21 2771 1882 21 1882 2771 bias=na,swish