projects
/
libreriscv.git
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
| inline |
side by side
(parent:
82afca3
)
(no commit message)
author
Xan
<Xan@web>
Wed, 25 Apr 2018 11:41:54 +0000
(12:41 +0100)
committer
IkiWiki
<ikiwiki.info>
Wed, 25 Apr 2018 11:41:54 +0000
(12:41 +0100)
Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn
patch
|
blob
|
history
diff --git
a/Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn
b/Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn
index 38026f87e2a62406e232143004acbaf04e20a32c..b76f22a700a2ad6b14f17eb75b630d5ae72267c2 100644
(file)
--- a/
Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn
+++ b/
Comparative_analysis_Harmonised_RVP_vs_Andes_Packed_SIMD_ISA_proposal.mdwn
@@
-27,7
+27,7
@@
Values for mm field (bits 12:13 above):
* mm = 10 -> use v1 as predicate mask, and use global saturation / rounding settings
* mm = 11 -> use ~v1 as predicate mask, and use global saturation / rounding settings
-## Register file
+## Register file
comparison
The default Harmonised RVP GPR register file is divided into a lower bank of Vector[INT8] and an upper bank of Vector[INT16].
In contrast, the Andes Packed SIMD ISA permits any GPR to be used for either INT8 or INT16 vector operations