add twin butterfly page (stub)

[libreriscv.git] / openpower / sv / remap.mdwn

diff --git a/openpower/sv/remap.mdwn b/openpower/sv/remap.mdwn
index 89fe28aa8f83392b1ee99912b8396aba594028dc..2deebef865dcbee92809c621707ee89717803b82 100644 (file)
--- a/openpower/sv/remap.mdwn
+++ b/openpower/sv/remap.mdwn
@@ -198,6 +198,26 @@ of the Micro-Architecture the Hardware Engineer should first consider
 how best to process the exact same equivalent loop-unrolled instruction
 stream.*
 
+## Horizontal-Parallelism Hint
+
+`SVSTATE.hphint` is an indicator to hardware of how many elements are 100%
+fully independent.  Hardware is permitted to assume that groups of elements
+up to `hphint` in size need not have Register (or Memory) Hazards created
+between them (including when `hphint > VL`).
+
+If care is not taken in setting `hphint` correctly it may wreak havoc.
+For example Matrix Outer Product relies on the innermost loop computations
+being independent.  If `hphint` is set to greater than the Outer Product
+depth then data corruption is guaranteed to occur.
+
+Likewise on FFTs it is assumed that each layer of the RADIX2 triple-loop
+is independent, but that there is strict *inter-layer* Register Hazards.
+Therefore if `hphint` is set to greater than the RADIX2 width of the FFT,
+data corruption is guaranteed.
+
+Thus the key message is that setting `hphint` requires in-depth knowledge
+of the REMAP Algorithm Schedules, given in the Appendix.
+
 ## REMAP types
 
 This section summarises the motivation for each REMAP Schedule
@@ -317,6 +337,10 @@ all *already* critically depend on overlapping Reads/Writes: Matrix
 uses overlapping registers as accumulators.  Thus the Register Hazard
 Management needed by Indexed REMAP *has* to be in place anyway.
 
+*Programmer's Note: `hphint` may be used to help hardware identify
+parallelism opportunities but it is critical to remember that the
+groupings are by `FLOOR(step/MAXVL)` not `FLOOR(REMAP(step)/MAXVL)`.*
+
 The cost compared to Matrix and other REMAPs (and Pack/Unpack) is
 clearly that of the additional reading of the GPRs to be used as Indices,
 plus the setup cost associated with creating those same Indices.
@@ -348,7 +372,7 @@ Interrupts and exceptions
 can therefore also be precise.  The final result will be in the first
 non-predicate-masked-out destination element, but due again to
 the deterministic schedule programmers may find uses for the intermediate
-results.
+results, even for non-commutative Defined Word operations.
 
 When Rc=1 a corresponding Vector of co-resultant CRs is also
 created.  No special action is taken: the result *and its CR Field*