From 986e7d007d0a0e603767a40d3797d27cd6627353 Mon Sep 17 00:00:00 2001
From: Luke Kenneth Casson Leighton <lkcl@lkcl.net>
Date: Tue, 6 Feb 2024 13:51:53 +0000
Subject: [PATCH] bug 676: tidyup and add svp64 assembler to cookbook page

---
 openpower/sv/cookbook/fortran_maxloc.mdwn | 61 ++++++++++++++++-------
 1 file changed, 44 insertions(+), 17 deletions(-)

diff --git a/openpower/sv/cookbook/fortran_maxloc.mdwn b/openpower/sv/cookbook/fortran_maxloc.mdwn
index b06e34b4f..367d0d12a 100644
--- a/openpower/sv/cookbook/fortran_maxloc.mdwn
+++ b/openpower/sv/cookbook/fortran_maxloc.mdwn
@@ -1,26 +1,28 @@
 # Fortran MAXLOC SVP64 demo
 
+<https://bugs.libre-soc.org/show_bug.cgi?id=676>
+
 MAXLOC is a notoriously difficult function for SIMD to cope with.
-SVP64 however has similar capabilities to Z80 CPIR and LDIR
+Typical approaches are to perform leaf-node (depth-first) parallel
+operations, merging the results mapreduce-style to guage a final
+index.
 
-<https://bugs.libre-soc.org/show_bug.cgi?id=676>
+SVP64 however has similar capabilities to Z80 CPIR and LDIR and
+therefore hardware may transparently implement back-end parallel
+operations whilst the developer programs in a simple sequential
+algorithm.
+
+A clear reference implementation of MAXLOC is as follows:
 
 ```
-int m2(int * const restrict a, int n) 
-{ 
-   int m, nm; 
-   int i; 
-
-   m = INT_MIN; 
-   nm = -1; 
-   for (i=0; i<n; i++) 
-   { 
-       if (a[i] > m) 
-       { 
-           m = a[i]; 
-           nm = i; 
-       } 
-    } 
+int maxloc(int * const restrict a, int n) {
+    int m, nm = INT_MIN, 0;
+    for (int i=0; i<n; i++) {
+        if (a[i] > m) {
+            m = a[i];
+            nm = i;
+        }
+    }
     return nm; 
 }
 ```
@@ -87,6 +89,31 @@ search seems to be a common technique.
 
 <https://github.com/jvdd/argminmax/blob/main/src/simd/simd_u64.rs>
 
+# Implementation in SVP64 Assembler
+
+The core algorithm (inner part, in-register) is below: 11 instructions.
+Loading of data, and offsetting the "core" below is relatively
+straightforward: estimated another 6 instructions and needing one
+more branch (outer loop).
+
+```
+# while (i<n)
+setvl 2,0,4,0,1,1            # set MVL=4, VL=MIN(MVL,CTR)
+#    while (i<n and a[i]<=m) : i += 1
+sv.cmp/ff=gt/m=ge *0,0,*10,4 # truncates VL to min
+sv.creqv *16,*16,*16         # set mask on already-tested
+setvl 2,0,4,0,1,1            # set MVL=4, VL=MIN(MVL,CTR)
+mtcrf 128, 0                 # clear CR0 (in case VL=0?)
+#    while (i<n and a[i]>m):
+sv.minmax./ff=le/m=ge 4,*10,4,1 # uses r4 as accumulator
+crternlogi 0,1,2,127         # test greater/equal or VL=0
+sv.crand *19,*16,0           # clear if CR0.eq=0
+#      nm = i (count masked bits. could use crweirds here TODO)
+sv.svstep/mr/m=so 1, 0, 6, 1 # svstep: get vector dststep
+sv.creqv *16,*16,*16         # set mask on already-tested
+bc 12,0, -0x40               # CR0 lt bit clear, branch back
+```
+
 [[!tag svp64_cookbook ]]
 
 
-- 
2.30.2