From 1f23b3bc515f1d66968d958c5d99550c11528b77 Mon Sep 17 00:00:00 2001
From: Luke Kenneth Casson Leighton <lkcl@lkcl.net>
Date: Tue, 20 Nov 2018 20:30:26 +0000
Subject: [PATCH] notes on LD pseudocode

---
 simple_v_extension/specification.mdwn | 29 +++++++++++++++++----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/simple_v_extension/specification.mdwn b/simple_v_extension/specification.mdwn
index 5e038cf10..5e93369f5 100644
--- a/simple_v_extension/specification.mdwn
+++ b/simple_v_extension/specification.mdwn
@@ -1279,29 +1279,36 @@ elements are treated as indirection addresses.  Simplified
 pseudo-code would look like this:
 
     function op_load(rd, rs) # LD not VLD!
-      rd = int_csr[rd].active ? int_csr[rd].regidx : rd;
-      rs = int_csr[rs].active ? int_csr[rs].regidx : rs;
+      rdv = int_csr[rd].active ? int_csr[rd].regidx : rd;
+      rsv = int_csr[rs].active ? int_csr[rs].regidx : rs;
       ps = get_pred_val(FALSE, rs); # predication on src
       pd = get_pred_val(FALSE, rd); # ... AND on dest
       for (int i = 0, int j = 0; i < VL && j < VL;):
         if (int_csr[rs].isvec) while (!(ps & 1<<i)) i++;
         if (int_csr[rd].isvec) while (!(pd & 1<<j)) j++;
         if (int_csr[rd].isvec)
-          srcbase = ireg[rs+i];
+          srcbase = ireg[rsv+i];
         else
-          srcbase = ireg[rs] + i * XLEN/8; # offset in bytes
-        ireg[rd+j] <= mem[srcbase + imm_offs];
+          srcbase = ireg[rsv] + i * XLEN/8; # offset in bytes
+        ireg[rdv+j] <= mem[srcbase + imm_offs];
         if (!int_csr[rs].isvec &&
             !int_csr[rd].isvec) break # scalar-scalar LD
         if (int_csr[rs].isvec) i++;
         if (int_csr[rd].isvec) j++;
 
-The test for whether both source and destination are scalar is
-what makes the above pseudo-code provide the "standard" RV Base
-behaviour for LD operations.  The offset in bytes (XLEN/8)
-changes depending on whether the operation is a LB (1 byte),
-LH (2 byes), LW (4 bytes) or LD (8 bytes), and also whether the element
-width is over-ridden (see special element width section).
+Notes:
+
+* For simplicity, zeroing and elwidth is not included in the above:
+  the key focus here is the decision-making for srcbase; vectorised
+  rs means use sequentially-numbered registers as the indirection
+  address, and scalar rs is "offset" mode.
+* The test towards the end for whether both source and destination are
+  scalar is what makes the above pseudo-code provide the "standard" RV
+  Base behaviour for LD operations.
+* The offset in bytes (XLEN/8) changes depending on whether the
+  operation is a LB (1 byte), LH (2 byes), LW (4 bytes) or LD
+  (8 bytes), and also whether the element width is over-ridden
+  (see special element width section).
 
 ## Compressed Stack LOAD / STORE Instructions <a name="c_ld_st"></a>
 
-- 
2.30.2