(no commit message)

diff --git a/openpower/sv/ldst.mdwn b/openpower/sv/ldst.mdwn
index 765f43a7b683997b696c1a6a4e83984943fcc4ac..b5aa548e89c9ef768b02e1ab6b766a865a5d9c34 100644 (file)
--- a/openpower/sv/ldst.mdwn
+++ b/openpower/sv/ldst.mdwn
@@ -386,19 +386,21 @@ others like it provide an explicit operation width.  There are therefore
 *three* widths involved:
 
 * operation width (lb=8, lh=16, lw=32, ld=64)
-* src elelent width override (8/16/32/default)
+* src element width override (8/16/32/default)
 * destination element width override (8/16/32/default)
 
 Some care is therefore needed to express and make clear the transformations, 
 which are expressly in this order:
 
+* Calculate the Effective Address from RA at full width
+  but (on Indexed Load) allow srcwidth overrides on RB 
 * Load at the operation width (lb/lh/lw/ld) as usual
 * byte-reversal as usual
 * Non-saturated mode:
-   - zero-extension or truncation from operation width to source elwidth
-   - zero/truncation to dest elwidth
+   - zero-extension or truncation from operation width to dest elwidth
+   - place result in destination at dest elwidth
 * Saturated mode:
-   - Sign-extension or truncation from operation width to source width
+   - Sign-extension or truncation from operation width to dest width
    - signed/unsigned saturation down to dest elwidth
 
 In order to respect OpenPOWER v3.0B Scalar behaviour the memory side
@@ -466,16 +468,17 @@ and other modes have all been removed, for clarity and simplicity:
 
         # check saturation.
         if svpctx.saturation_mode:
-            ... saturation adjustment...
+            # ... saturation adjustment...
+            memread = clamp(memread, op_width, svctx.dest_elwidth)
         else:
-            # truncate/extend to over-ridden source width.
-            memread = adjust_wid(memread, op_width, svctx.src_elwidth)
+            # truncate/extend to over-ridden dest width.
+            memread = adjust_wid(memread, op_width, svctx.dest_elwidth)
 
         # takes care of inserting memory-read (now correctly byteswapped)
         # into regfile underlying LE-defined order, into the right place
         # within the NEON-like register, respecting destination element
         # bitwidth, and the element index (j)
-        set_polymorphed_reg(RT, svctx.dest_bitwidth, j, memread)
+        set_polymorphed_reg(RT, svctx.dest_elwidth, j, memread)
 
         # increments both src and dest element indices (no predication here)
         i++;