RISC-V vector: correct references

manuscrit/20_foundations/10_cpu_arch.tex

@@ -258,4 +258,6 @@ only one such instruction per two cycles. Even in this case, there are clear
 efficiency benefits: while there is no real gain in the backend, the frontend
 has only one instruction to decode, rename, etc., greatly alleviating frontend
 pressure. This is for instance the case of the implementation of the
-RISC-V~\cite{riscv_isa} vector extension, \qtodo{ref Filippo Mantovani}
+RISC-V~\cite{riscv_isa} vector extension, supporting up to 256 double-precision
+floats in a single operation, while the hardware supports far less in one
+cycle~\cite{filippo_riscv_vector, filippo_acaces23}.

manuscrit/biblio/misc.bib

@@ -188,3 +188,18 @@
   pages={1--32},
   year={2011}
 }
+
+@inproceedings{filippo_riscv_vector,
+  title={Software Development Vehicles to enable extended and early co-design: a RISC-V and HPC case of study},
+  author={Mantovani, Filippo and Vizcaino, Pablo and Banchelli, Fabio and Garcia-Gasulla, Marta and Ferrer, Roger and Ieronymakis, Georgios and Dimou, Nikolaos and Papaefstathiou, Vassilis and Labarta, Jesus},
+  booktitle={International Conference on High Performance Computing},
+  pages={526--537},
+  year={2023},
+  organization={Springer}
+}
+@misc{filippo_acaces23,
+    author={Mantovani, Filippo},
+    year={2023},
+    month={July},
+    howpublished={Private communication during the ACACES summer school},
+}