t1
t1 copied to clipboard
chipsalliance
### Reproduce steps 1. Checkout branch `binder-again`. 2. https://github.com/chipsalliance/t1/blob/925e01e361bff268b51bbd83ebd0e4a693d46c26/nix/t1/default.nix#L81 Specifying `use-binder = true;` to use the Binder Framework, commenting it out to use the old Serialization Flow. 3. Run `nix...
- [build system] dedup run-test.py - [WIP] [testcases] add mmm_mem cases
The basic verification idea of T1 IP is based on the online difftest. However when we are getting bigger and bigger, verification becomes a new problem, which we need to...
Hello, I'm a beginner of t1. I wang to figuer it out that does t1 have a benchmark? if not , how can we compare the performance between t1 and...
The current uArch of T1 is not a **micro** arch now, appending to a lot of parameters, it is going to be another giant In order to deliver this to...
Originally in RocketChip, we use SBT to generate jar and execute it to generate Verilog, which was a nightmare to maintain, thus we eventually switch to mill for managing this...
There is a conv_2d_nchw_fchw im2col implementation(conv2d-nchw-fchw-im2col.mlir) containing `llvm.sdiv` after lowering, which will cause __divdi3 -related errors as follows: ``` bash-5.2$ time mill -i 'tests.run[conv2d-nchw-fchw-im2col.mlir].run' [7/438] tests.cases.buddy[conv2d-nchw-fchw-im2col.mlir].elf ld.lld: error: undefined symbol:...
Recently buddy-benchmark has implemented the e2e compilation of "EfficientNet-Quant" (see https://github.com/buddy-compiler/buddy-benchmark/tree/main/benchmarks/DeepLearning/Models/EfficientNet-Quant), a typical deep learning quantized model without float point operations involved in the lowering process. Executing it on the...