From 54b21d11782812a30f05445add6f21d42e1607d1 Mon Sep 17 00:00:00 2001
From: lkcl <lkcl@web>
Date: Wed, 26 Apr 2023 17:10:14 +0100
Subject: [PATCH]

---
 openpower/sv/cookbook/conflictd.mdwn | 52 ++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/openpower/sv/cookbook/conflictd.mdwn b/openpower/sv/cookbook/conflictd.mdwn
index 4d2b56ab0..87f9a8d55 100644
--- a/openpower/sv/cookbook/conflictd.mdwn
+++ b/openpower/sv/cookbook/conflictd.mdwn
@@ -1,3 +1,55 @@
 [[!tag svp64_cookbook ]]
 
 <https://libre-soc.org/openpower/sv/vector_ops/discussion/>
+
+This is based on the AVX512 conflict detection instruction.  Internally the logic is used to detect address conflicts in multi-issue LD/ST operations.  Two arrays of values are given: the indices are compared and duplicates reported in a triangular fashion.  the instruction may be used for histograms (computed in parallel)
+
+    input = [100, 100,   3, 100,   5, 100, 100,   3]
+    conflict result = [
+         0b00000000,    // Note: first element always zero
+         0b00000001,    // 100 is present on #0
+         0b00000000,
+         0b00000011,    // 100 is present on #0 and #1
+         0b00000000,
+         0b00001011,    // 100 is present on #0, #1, #3
+         0b00011011,    // .. and #4
+         0b00000100     // 3 is present on #2
+    ]
+
+Pseudocode:
+
+    for i in range(VL):
+        for j in range(1, i):
+            if src1[i] == src2[j]:
+                result[j] |= 1<<i
+
+Idea 1: implement this as a Triangular Schedule, Vertical-First Mode,
+  using `mfcrweird` and `cmpi`. first triangular schedule on src1,
+secpnd on src2.
+
+Idea 2: implement using outer loop on varying setvl Horizontal-First
+with `1<<r3` predicate mask for src2 as scalar, creates CR field vector, transfer into INT with mfcrweird then OR into the
+result.
+
+```
+    li r3, target
+    li result, 0
+    for i in range(target):
+        setvl target
+        addi r3, r3, -1 # shift 1<<r3 predicate down by one
+        sv.addi/sm=1<<r3 t0, src1.v, 0 # copy src1[i]
+        sv.cmpi src2.v, t0 # compare src2 vector to scalar
+        sv.mfcrweird t1, cr0.v, eq # copy CR eq result bits to t1
+        or result, result, t1
+```
+
+See [[sv/cr_int_predication]] for full details on the crweird instructions:
+the primary important aspect here is that a Vector of CR Field's EQ bits is
+transferred into a single GPR.  The secondary important aspect is that VL
+is being adjusted in each loop, testing successively more of the input
+vector against a given scalar, each time.
+
+To investigate:
+
+* <https://stackoverflow.com/questions/39266476/how-to-speed-up-this-histogram-of-lut-lookups>
+* <https://stackoverflow.com/questions/39913707/how-do-the-conflict-detection-instructions-make-it-easier-to-vectorize-loops>
-- 
2.30.2