X-Git-Url: https://git.libre-soc.org/?a=blobdiff_plain;f=simple_v_extension%2Fsimple_v_chennai_2018.tex;h=180519bea82f022c0d1b3f2dd5ffc91326358497;hb=27ab55401456175de16e2f0700a10beeeeb2a52c;hp=b0561901007c781f29b81b0c6216ef09d8a82d6d;hpb=c0580a67e43d4bdaa0dd7c8ee85da4033674866e;p=libreriscv.git

diff --git a/simple_v_extension/simple_v_chennai_2018.tex b/simple_v_extension/simple_v_chennai_2018.tex
index b05619010..180519bea 100644
--- a/simple_v_extension/simple_v_chennai_2018.tex
+++ b/simple_v_extension/simple_v_chennai_2018.tex
@@ -15,9 +15,10 @@
     \vspace{32pt}
     \Large{Flexible Vectorisation}\\
     \Large{(aka not so Simple-V?)}\\
+    \Large{(aka How to Parallelise the RISC-V ISA)}\\
     \vspace{24pt}
     \Large{[proposed for] Chennai 9th RISC-V Workshop}\\
-    \vspace{24pt}
+    \vspace{16pt}
     \large{\today}
   \end{center}
 }
@@ -28,8 +29,8 @@
  \begin{itemize}
    \item The Designers of RISC-V\vspace{15pt}
    \item The RVV Working Group and contributors\vspace{15pt}
-   \item Jacob Bachmeyer, Xan Phung, Chuanhua Chang,\\
-	     Guy Lemurieux, Jonathan Neuschafer, Roger Bruisse,
+   \item Allen Baum, Jacob Bachmeyer, Xan Phung, Chuanhua Chang,\\
+	     Guy Lemurieux, Jonathan Neuschafer, Roger Brussee,
 	     and others\vspace{15pt}
    \item ISA-Dev Group Members\vspace{10pt}
   \end{itemize}
@@ -39,15 +40,15 @@
 \frame{\frametitle{Quick refresher on SIMD}
 
  \begin{itemize}
-   \item SIMD very easy to implement (and very seductive)\vspace{10pt}
-   \item Parallelism is in the ALU\vspace{10pt}
-   \item Zero-to-Negligeable impact for rest of core\vspace{10pt}
+   \item SIMD very easy to implement (and very seductive)\vspace{8pt}
+   \item Parallelism is in the ALU\vspace{8pt}
+   \item Zero-to-Negligeable impact for rest of core\vspace{8pt}
   \end{itemize}
   Where SIMD Goes Wrong:\vspace{10pt}
    \begin{itemize}
    \item See "SIMD instructions considered harmful"
-   https://www.sigarch.org/simd-instructions-considered-harmful
-   \item Corner-cases alone are extremely complex.\\
+   https://sigarch.org/simd-instructions-considered-harmful
+   \item Setup and corner-cases alone are extremely complex.\\
 	     Hardware is easy, but software is hell.
    \item O($N^{6}$) ISA opcode proliferation!\\
 	     opcode, elwidth, veclen, src1-src2-dest hi/lo
@@ -59,14 +60,14 @@
  \begin{itemize}
    \item Extremely powerful (extensible to 256 registers)\vspace{10pt}
    \item Supports polymorphism, several datatypes (inc. FP16)\vspace{10pt}
-   \item Requires a separate Register File\vspace{10pt}
-   \item Can be implemented as a separate pipeline\vspace{10pt}
+   \item Requires a separate Register File (16 w/ext to 256)\vspace{10pt}
+   \item Implemented as a separate pipeline (no impact on scalar)\vspace{10pt}
   \end{itemize}
   However...\vspace{10pt}
    \begin{itemize}
    \item 98 percent opcode duplication with rest of RV (CLIP)
    \item Extending RVV requires customisation not just of h/w:\\
-	     gcc and s/w also need customisation (and maintenance)
+	     gcc, binutils also need customisation (and maintenance)
   \end{itemize}
 }
 
@@ -82,29 +83,52 @@
 		 of pipeline setup, amount of state to context switch
 		 and software portability\vspace{4pt}
    \item How?
-	     By implicitly marking INT/FP regs as "Vectorised",\\
+	     By marking INT/FP regs as "Vectorised" and
+	     adding a level of indirection,
 	     SV expresses how existing instructions should act 
 	     on [contiguous] blocks of registers, in parallel.\vspace{4pt}
    \item What?
 		 Simple-V is an "API" that implicitly extends
-		 existing (scalar) instructions with explicit parallelisation. 
+		 existing (scalar) instructions with explicit parallelisation\\
+		 (i.e. SV is actually about parallelism NOT vectors per se)
+  \end{itemize}
+}
+
+
+\frame{\frametitle{What's the value of SV? Why adopt it even in non-V?}
+
+ \begin{itemize}
+   \item memcpy becomes much smaller (higher bang-per-buck)
+   \item context-switch (LOAD/STORE multiple): 1-2 instructions
+   \item Compressed instrs further reduces I-cache (etc.)
+   \item Greatly-reduced I-cache load (and less reads)
+   \item Amazingly, SIMD becomes (more) tolerable\\
+	     (corner-cases for setup and teardown are gone)
+   \item Modularity/Abstraction in both the h/w and the toolchain.
+  \end{itemize}
+  Note:
+   \begin{itemize}
+   \item It's not just about Vectors: it's about instruction effectiveness
+   \item Anything that makes SIMD tolerable has to be a good thing
+   \item Anything implementor is not interested in HW-optimising,\\
+	     let it fall through to exceptions (implement as a trap).
   \end{itemize}
 }
 
 
-\frame{\frametitle{How does Simple-V relate to RVV?}
+\frame{\frametitle{How does Simple-V relate to RVV? What's different?}
 
  \begin{itemize}
    \item RVV very heavy-duty (excellent for supercomputing)\vspace{10pt}
    \item Simple-V abstracts parallelism (based on best of RVV)\vspace{10pt}
    \item Graded levels: hardware, hybrid or traps (fit impl. need)\vspace{10pt}
-   \item Even Compressed instructions become vectorised\vspace{10pt}
+   \item Even Compressed become vectorised (RVV can't)\vspace{10pt}
   \end{itemize}
   What Simple-V is not:\vspace{10pt}
    \begin{itemize}
    \item A full supercomputer-level Vector Proposal
    \item A replacement for RVV (SV is designed to be over-ridden\\
-	     by - or augmented to become, or just be replaced by  - RVV)
+	     by - or augmented to become - RVV)
   \end{itemize}
 }
 
@@ -112,17 +136,19 @@
 \frame{\frametitle{How is Parallelism abstracted in Simple-V?}
 
  \begin{itemize}
-   \item Register "typing" turns any op into an implicit Vector op\vspace{10pt}
+   \item Register "typing" turns any op into an implicit Vector op:\\
+         registers are reinterpreted through a level of indirection
    \item Primarily at the Instruction issue phase (except SIMD)\\
          Note: it's ok to pass predication through to ALU (like SIMD)
    \item Standard (and future, and custom) opcodes now parallel\vspace{10pt}
   \end{itemize}
-  Notes:\vspace{6pt}
+  Note: EVERYTHING is parallelised:
    \begin{itemize}
-   \item LOAD/STORE (inc. C.LD and C.ST, LD.X: everything)
+   \item All LOAD/STORE (inc. Compressed, Int/FP versions)
    \item All ALU ops (soft / hybrid / full HW, on per-op basis)
-   \item All branches become predication targets (C.FNE added)
+   \item All branches become predication targets (C.FNE added?)
    \item C.MV of particular interest (s/v, v/v, v/s)
+   \item FCVT, FMV, FSGNJ etc. very similar to C.MV
   \end{itemize}
 }
 
@@ -152,18 +178,44 @@
 % but MODIFYING the remaining "vectorised" op, subtracting the now
 % scalar ops from it.
 
+\frame{\frametitle{Predicated 8-parallel ADD: 1-wide ALU}
+ \begin{center}
+  \includegraphics[height=2.5in]{padd9_alu1.png}\\
+  {\bf \red Predicated adds are shuffled down: 6 cycles in total}
+ \end{center}
+}
+
+
+\frame{\frametitle{Predicated 8-parallel ADD: 4-wide ALU}
+ \begin{center}
+  \includegraphics[height=2.5in]{padd9_alu4.png}\\
+  {\bf \red Predicated adds are shuffled down: 4 in 1st cycle, 2 in 2nd}
+ \end{center}
+}
+
+
+\frame{\frametitle{Predicated 8-parallel ADD: 3 phase FIFO expansion}
+ \begin{center}
+  \includegraphics[height=2.5in]{padd9_fifo.png}\\
+  {\bf \red First cycle takes first four 1s; second takes the rest}
+ \end{center}
+}
+
+
 \frame{\frametitle{How are SIMD Instructions Vectorised?}
 
  \begin{itemize}
-   \item SIMD ALU(s) primarily unchanged\vspace{10pt}
-   \item Predication is added to each SIMD element (NO ZEROING!)\vspace{10pt}
-   \item End of Vector enables predication (NO ZEROING!)\vspace{10pt}
+   \item SIMD ALU(s) primarily unchanged\vspace{6pt}
+   \item Predication is added to each SIMD element\vspace{6pt}
+   \item Predication bits sent in groups to the ALU\vspace{6pt}
+   \item End of Vector enables (additional) predication\vspace{10pt}
   \end{itemize}
-  Considerations:\vspace{10pt}
+  Considerations:\vspace{4pt}
    \begin{itemize}
-   \item Many SIMD ALUs possible (parallel execution)\vspace{10pt}
-   \item Very long SIMD ALUs could waste die area (short vectors)\vspace{10pt}
-   \item Implementor free to choose (API remains the same)\vspace{10pt}
+   \item Many SIMD ALUs possible (parallel execution)
+   \item Implementor free to choose (API remains the same)
+   \item Unused ALU units wasted, but s/w DRASTICALLY simpler 
+   \item Very long SIMD ALUs could waste significant die area
   \end{itemize}
 }
 % With multiple SIMD ALUs at for example 32-bit wide they can be used 
@@ -171,11 +223,21 @@
 % or they can be used to cover several operations on totally different
 % vectors / registers.
 
+\frame{\frametitle{Predicated 9-parallel SIMD ADD}
+ \begin{center}
+  \includegraphics[height=2.5in]{padd9_simd.png}\\
+  {\bf \red 4-wide 8-bit SIMD, 4 bits of predicate passed to ALU}
+ \end{center}
+}
+
+
 \frame{\frametitle{What's the deal / juice / score?}
 
  \begin{itemize}
-   \item Standard Register File(s) overloaded with "vector span"\vspace{10pt}
-   \item Element width and type concepts remain same as RVV\vspace{10pt}
+   \item Standard Register File(s) overloaded with CSR "reg is vector"\\
+	     (see pseudocode slides for examples)
+   \item Element width (and type?) concepts remain same as RVV\\
+	     (CSRs give new size (and meaning?) to elements in registers)
    \item CSRs are key-value tables (overlaps allowed)\vspace{10pt}
   \end{itemize}
   Key differences from RVV:\vspace{10pt}
@@ -183,40 +245,116 @@
    \item Predication in INT regs as a BIT field (max VL=XLEN)
    \item Minimum VL must be Num Regs - 1 (all regs single LD/ST)
    \item SV may condense sparse Vecs: RVV lets ALU do predication
-   \item NO ZEROING: non-predicated elements are skipped
+   \item Choice to Zero or skip non-predicated elements
   \end{itemize}
 }
 
 
+\begin{frame}[fragile]
+\frametitle{ADD pseudocode (or trap, or actual hardware loop)}
+
+\begin{semiverbatim}
+function op\_add(rd, rs1, rs2, predr) # add not VADD!
+  int i, id=0, irs1=0, irs2=0;
+  for (i = 0; i < VL; i++)
+    if (ireg[predr] & 1<<i) # predication uses intregs
+       ireg[rd+id] <= ireg[rs1+irs1] + ireg[rs2+irs2];
+    if (reg\_is\_vectorised[rd]) \{ id += 1; \}
+    if (reg\_is\_vectorised[rs1]) \{ irs1 += 1; \}
+    if (reg\_is\_vectorised[rs2]) \{ irs2 += 1; \}
+\end{semiverbatim}
+
+  \begin{itemize}
+   \item Above is oversimplified: Reg. indirection left out (for clarity).
+   \item SIMD slightly more complex (case above is elwidth = default)
+   \item Scalar-scalar and scalar-vector and vector-vector now all in one
+   \item OoO may choose to push ADDs into instr. queue (v. busy!)
+  \end{itemize}
+\end{frame}
+
+% yes it really *is* ADD not VADD.  that's the entire point of
+% this proposal, that *standard* operations are overloaded to
+% become vectorised-on-demand
+
+
+\begin{frame}[fragile]
+\frametitle{Predication-Branch (or trap, or actual hardware loop)}
+
+\begin{semiverbatim}
+s1 = reg\_is\_vectorised(src1);
+s2 = reg\_is\_vectorised(src2);
+if (!s2 && !s1) goto branch;
+for (int i = 0; i < VL; ++i)
+  if (cmp(s1 ? reg[src1+i]:reg[src1],
+          s2 ? reg[src2+i]:reg[src2])
+         ireg[rs3] |= 1<<i;
+\end{semiverbatim}
+
+  \begin{itemize}
+   \item SIMD slightly more complex (case above is elwidth = default)  
+   \item If s1 and s2 both scalars, Standard branch occurs
+   \item Predication stored in integer regfile as a bitfield
+   \item Scalar-vector and vector-vector supported
+  \end{itemize}
+\end{frame}
+
+\begin{frame}[fragile]
+\frametitle{VLD/VLD.S/VLD.X (or trap, or actual hardware loop)}
+
+\begin{semiverbatim}
+if (unit-strided) stride = elsize;
+else stride = areg[as2]; // constant-strided
+for (int i = 0; i < VL; ++i)
+  if (preg\_enabled[rd] && ([!]preg[rd] & 1<<i))
+    for (int j = 0; j < seglen+1; j++)
+      if (reg\_is\_vectorised[rs2]) offs = vreg[rs2+i]
+      else offs = i*(seglen+1)*stride;
+      vreg[rd+j][i] = mem[sreg[base] + offs + j*stride]
+\end{semiverbatim}
+
+  \begin{itemize}
+   \item Again: elwidth != default slightly more complex
+   \item rs2 vectorised taken to implicitly indicate VLD.X
+  \end{itemize}
+\end{frame}
+
+
 \frame{\frametitle{Why are overlaps allowed in Regfiles?}
 
  \begin{itemize}
-   \item Same register(s) can have multiple "interpretations"\vspace{10pt}
-   \item xBitManip plus SIMD plus xBitManip = Hi/Lo bitops\vspace{10pt}
-   \item (32-bit GREV plus 4x8-bit SIMD plus 32-bit GREV)\vspace{10pt}
-   \item Same register(s) can be offset (no need for VSLIDE)\vspace{10pt}
-  \end{itemize}
-  Note:\vspace{10pt}
+   \item Same register(s) can have multiple "interpretations"
+   \item Set "real" register (scalar) without needing to set/unset CSRs.
+   \item xBitManip plus SIMD plus xBitManip = Hi/Lo bitops
+   \item (32-bit GREV plus 4x8-bit SIMD plus 32-bit GREV:\\
+	     GREV @ VL=N,wid=32; SIMD @ VL=Nx4,wid=8)
+   \item RGB 565 (video): BEXTW plus 4x8-bit SIMD plus BDEPW\\
+	     (BEXT/BDEP @ VL=N,wid=32; SIMD @ VL=Nx4,wid=8)
+   \item Same register(s) can be offset (no need for VSLIDE)\vspace{6pt}
+  \end{itemize}
+  Note:
    \begin{itemize}
-   \item xBitManip reduces O($N^{6}$) SIMD down to O($N^{3}$) \vspace{10pt}
-   \item Hi-Performance: Macro-op fusion (more pipeline stages?)\vspace{10pt}
+   \item xBitManip reduces O($N^{6}$) SIMD down to O($N^{3}$)
+   \item Hi-Performance: Macro-op fusion (more pipeline stages?)
   \end{itemize}
 }
 
 
-\frame{\frametitle{Why no Zeroing (place zeros in non-predicated elements)?}
+\frame{\frametitle{To Zero or not to place zeros in non-predicated elements?}
 
  \begin{itemize}
-   \item Zeroing is an implementation optimisation favouring OoO\vspace{8pt}
-   \item Simple implementations may skip non-predicated operations\vspace{8pt}
-   \item Simple implementations explicitly have to destroy data\vspace{8pt}
+   \item Zeroing is an implementation optimisation favouring OoO
+   \item Simple implementations may skip non-predicated operations
+   \item Simple implementations explicitly have to destroy data
    \item Complex implementations may use reg-renames to save power\\
 	     Zeroing on predication chains makes optimisation harder
+   \item Compromise: REQUIRE both (specified in predication CSRs).
   \end{itemize}
-  Considerations:\vspace{10pt}
+  Considerations:
   \begin{itemize}
-   \item Complex not really impacted, Simple impacted a LOT
-   \item Overlapping "Vectors" may issue overlapping ops
+   \item Complex not really impacted, simple impacted a LOT\\
+         with Zeroing... however it's useful (memzero)
+   \item Non-zero'd overlapping "Vectors" may issue overlapping ops\\
+	     (2nd op's predicated elements slot in 1st's non-predicated ops)
    \item Please don't use Vectors for "security" (use Sec-Ext)
   \end{itemize}
 }
@@ -231,10 +369,11 @@
 \frame{\frametitle{Predication key-value CSR store}
 
  \begin{itemize}
-   \item key is int regfile number or FP regfile number (1 bit)\vspace{10pt}
-   \item register to be predicated if referred to (5 bits, key)\vspace{10pt}
-   \item register to store actual predication in (5 bits, value)\vspace{10pt}
-   \item predication is inverted (1 bit)\vspace{10pt}
+   \item key is int regfile number or FP regfile number (1 bit)\vspace{6pt}
+   \item register to be predicated if referred to (5 bits, key)\vspace{6pt}
+   \item register to store actual predication in (5 bits, value)\vspace{6pt}
+   \item predication is inverted Y/N (1 bit)\vspace{6pt}
+   \item non-predicated elements are to be zero'd Y/N (1 bit)\vspace{6pt}
   \end{itemize}
   Notes:\vspace{10pt}
    \begin{itemize}
@@ -245,80 +384,113 @@
 }
 
 
-\frame{\frametitle{Register key-value CSR store}
+\begin{frame}[fragile]
+\frametitle{Predication key-value CSR table decoding pseudocode}
+
+\begin{semiverbatim}
+struct pred fp\_pred[32];
+struct pred int\_pred[32];
+
+for (i = 0; i < 16; i++) // 16 CSRs?
+   tb = int\_pred if CSRpred[i].type == 0 else fp\_pred
+   idx = CSRpred[i].regidx
+   tb[idx].zero     = CSRpred[i].zero
+   tb[idx].inv      = CSRpred[i].inv
+   tb[idx].predidx  = CSRpred[i].predidx
+   tb[idx].enabled  = true
+\end{semiverbatim}
 
  \begin{itemize}
-   \item key is int regfile number or FP regfile number (1 bit)\vspace{10pt}
-   \item register to be predicated if referred to (5 bits, key)\vspace{10pt}
-   \item register to store actual predication in (5 bits, value)\vspace{10pt}
-   \item TODO\vspace{10pt}
+   \item All 64 (int and FP) Entries zero'd before setting
+   \item Might be a bit complex to set up (TBD)
   \end{itemize}
-  Notes:\vspace{10pt}
-   \begin{itemize}
-   \item Table should be expanded out for high-speed implementations
-   \item Multiple "keys" (and values) theoretically permitted
-   \item RVV rules about deleting higher-indexed CSRs followed
-  \end{itemize}
-}
+
+\end{frame}
 
 
 \begin{frame}[fragile]
-\frametitle{ADD pseudocode (or trap, or actual hardware loop)}
+\frametitle{Get Predication value pseudocode}
 
 \begin{semiverbatim}
-function op_add(rd, rs1, rs2, predr) # add not VADD!
-  int i, id=0, irs1=0, irs2=0;
-  for (i=0; i < MIN(VL, vectorlen[rd]); i++)
-    if (ireg[predr] & 1<<i) # predication uses intregs
-       ireg[rd+id] <= ireg[rs1+irs1] + ireg[rs2+irs2];
-    if (reg_is_vectorised[rd]) \{ id += 1; \}
-    if (reg_is_vectorised[rs1]) \{ irs1 += 1; \}
-    if (reg_is_vectorised[rs2]) \{ irs2 += 1; \}
+def get\_pred\_val(bool is\_fp\_op, int reg):
+   tb = int\_pred if is\_fp\_op else fp\_pred
+   if (!tb[reg].enabled):
+      return ~0x0              // all ops enabled
+   predidx = tb[reg].predidx   // redirection occurs HERE
+   predicate = intreg[predidx] // actual predicate HERE
+   if (tb[reg].inv):
+      predicate = ~predicate
+   return predicate
 \end{semiverbatim}
 
-  \begin{itemize}
-   \item SIMD slightly more complex (case above is elwidth = default)
-   \item Scalar-scalar and scalar-vector and vector-vector now all in one
-   \item OoO may choose to push ADDs into instr. queue (v. busy!)
+ \begin{itemize}
+   \item References different (internal) mapping table for INT or FP
+   \item Actual predicate bitmask ALWAYS from the INT regfile
   \end{itemize}
+
 \end{frame}
 
+
+\frame{\frametitle{Register key-value CSR store}
+
+ \begin{itemize}
+   \item key is int regfile number or FP regfile number (1 bit)\vspace{6pt}
+   \item treated as vector if referred to in op (5 bits, key)\vspace{6pt}
+   \item starting register to actually be used (5 bits, value)\vspace{6pt}
+   \item element bitwidth: default/8/16/32/64/rsvd (3 bits)\vspace{6pt}
+   \item element type: still under consideration\vspace{6pt}
+  \end{itemize}
+  Notes:\vspace{10pt}
+   \begin{itemize}
+   \item Same notes apply (previous slide) as for predication CSR table
+   \item Level of indirection has implications for pipeline latency
+  \end{itemize}
+}
+
+
 \begin{frame}[fragile]
-\frametitle{Predication-Branch (or trap, or actual hardware loop)}
+\frametitle{Register key-value CSR table decoding pseudocode}
 
 \begin{semiverbatim}
-s1 = vectorlen[src1] > 1;
-s2 = vectorlen[src2] > 1;
-for (int i = 0; i < VL; ++i)
-   preg[rs3] |= 1 << cmp(s1 ? reg[src1+i] : reg[src1],
-                         s2 ? reg[src2+i] : reg[src2]);
+struct vectorised fp\_vec[32];
+struct vectorised int\_vec[32];
+
+for (i = 0; i < 16; i++) // 16 CSRs?
+   tb = int\_vec if CSRvectortb[i].type == 0 else fp\_vec
+   idx = CSRvectortb[i].regidx
+   tb[idx].elwidth  = CSRpred[i].elwidth
+   tb[idx].regidx   = CSRpred[i].regidx
+   tb[idx].isvector = true
 \end{semiverbatim}
 
-  \begin{itemize}
-   \item SIMD slightly more complex (case above is elwidth = default)  
-   \item If s1 and s2 both scalars, Standard branch occurs
-   \item Predication stored in integer regfile as a bitfield
-   \item Scalar-vector and vector-vector supported
+ \begin{itemize}
+   \item All 64 (int and FP) Entries zero'd before setting
+   \item Might be a bit complex to set up (TBD)
   \end{itemize}
+
 \end{frame}
 
+
 \begin{frame}[fragile]
-\frametitle{LD/LD.S/LD.X (or trap, or actual hardware loop)}
+\frametitle{ADD pseudocode with redirection, this time}
 
 \begin{semiverbatim}
-if (unit-strided) stride = elsize;
-else stride = areg[as2]; // constant-strided
-for (int i = 0; i < VL; ++i)
-  if (preg_enabled[rd] && ([!]preg[rd] & 1<<i))
-    for (int j = 0; j < seglen+1; j++)
-      if (vectorised[rs2]) offs = vreg[rs2][i]
-      else offs = i*(seglen+1)*stride;
-      vreg[rd+j][i] = mem[sreg[base] + offs + j*stride]
+function op\_add(rd, rs1, rs2) # add not VADD!
+  int i, id=0, irs1=0, irs2=0;
+  rd  = int\_vec[rd ].isvector ? int\_vec[rd ].regidx : rd;
+  rs1 = int\_vec[rs1].isvector ? int\_vec[rs1].regidx : rs1;
+  rs2 = int\_vec[rs2].isvector ? int\_vec[rs2].regidx : rs2;
+  predval = get\_pred\_val(FALSE, rd);
+  for (i = 0; i < VL; i++)
+    if (predval \& 1<<i) # predication uses intregs
+       ireg[rd+id] <= ireg[rs1+irs1] + ireg[rs2+irs2];
+    if (int\_vec[rd ].isvector)  \{ id += 1; \}
+    if (int\_vec[rs1].isvector)  \{ irs1 += 1; \}
+    if (int\_vec[rs2].isvector)  \{ irs2 += 1; \}
 \end{semiverbatim}
 
   \begin{itemize}
-   \item Again: SIMD slightly more complex
-   \item rs2 vectorised taken to implicitly indicate LD.X
+   \item SIMD (elwidth != default) not covered above
   \end{itemize}
 \end{frame}
 
@@ -326,23 +498,48 @@ for (int i = 0; i < VL; ++i)
 \frame{\frametitle{C.MV extremely flexible!}
 
  \begin{itemize}
-   \item scalar-to-vector (w/no pred): VSPLAT
-   \item scalar-to-vector (w/dest-pred): Sparse VSPLAT
-   \item scalar-to-vector (w/single dest-pred): VINSERT
-   \item vector-to-scalar (w/src-pred): VEXTRACT
-   \item vector-to-vector (w/no pred): Vector Copy
-   \item vector-to-vector (w/src xor dest pred): Sparse Vector Copy
-   \item vector-to-vector (w/src and dest pred): Vector Shuffle
-  \end{itemize}
-  \vspace{8pt}
-  Notes:\vspace{10pt}
+   \item scalar-to-vector (w/ no pred): VSPLAT
+   \item scalar-to-vector (w/ dest-pred): Sparse VSPLAT
+   \item scalar-to-vector (w/ 1-bit dest-pred): VINSERT
+   \item vector-to-scalar (w/ [1-bit?] src-pred): VEXTRACT
+   \item vector-to-vector (w/ no pred): Vector Copy
+   \item vector-to-vector (w/ src pred): Vector Gather
+   \item vector-to-vector (w/ dest pred): Vector Scatter
+   \item vector-to-vector (w/ src \& dest pred): Vector Gather/Scatter
+  \end{itemize}
+  \vspace{4pt}
+  Notes:
    \begin{itemize}
-   \item Really powerful!
-   \item Any other options?
+   \item Surprisingly powerful!
+   \item Same arrangement for FVCT, FMV, FSGNJ etc.
   \end{itemize}
 }
 
 
+\begin{frame}[fragile]
+\frametitle{MV pseudocode with predication}
+
+\begin{semiverbatim}
+function op\_mv(rd, rs) # MV not VMV!
+  rd = int\_vec[rd].isvector ? int\_vec[rd].regidx : rd;
+  rs = int\_vec[rs].isvector ? int\_vec[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\_vec[rs].isvec) while (!(ps \& 1<<i)) i++;
+    if (int\_vec[rd].isvec) while (!(pd \& 1<<j)) j++;
+    ireg[rd+j] <= ireg[rs+i];
+    if (int\_vec[rs].isvec) i++;
+    if (int\_vec[rd].isvec) j++;
+\end{semiverbatim}
+
+  \begin{itemize}
+   \item elwidth != default not covered above (might be a bit hairy)
+   \item Ending early with 1-bit predication not included (VINSERT)
+  \end{itemize}
+\end{frame}
+
+
 \frame{\frametitle{Opcodes, compared to RVV}
 
  \begin{itemize}
@@ -358,72 +555,141 @@ for (int i = 0; i < VL; ++i)
 }
 
 
-\frame{\frametitle{Under consideration}
+\begin{frame}[fragile]
+\frametitle{Example c code: DAXPY}
 
- \begin{itemize}
-   \item Is C.FNE actually needed?\vspace{10pt}
-   \item Can VSELECT be removed? (it's really complex)\vspace{10pt}
-   \item Can CLIP be done as a CSR (mode, like elwidth)\vspace{10pt}
-   \item SIMD saturation (etc.) also set as a mode?\vspace{10pt}
-   \item C.MV src predication no different from dest predication\\
-         What to do? Make one have different meaning?\vspace{10pt}
-   \item 8/16-bit ops is it worthwhile adding a "start offset"? \\
-         (a bit like misaligned addressing... for registers)\\
-         or just use predication to skip start?\vspace{10pt}
+\begin{semiverbatim}
+    void daxpy(size_t n, double a,
+               const double x[], double y[])
+    \{
+     for (size_t i = 0; i < n; i++) \{
+       y[i] = a*x[i] + y[i];
+     \}
+    \}
+\end{semiverbatim}
+
+  \begin{itemize}
+   \item See "SIMD Considered Harmful" for SIMD/RVV analysis\\
+	   https://sigarch.org/simd-instructions-considered-harmful/
   \end{itemize}
-}
 
 
-\frame{\frametitle{Summary}
+\end{frame}
+
+
+\begin{frame}[fragile]
+\frametitle{RVV DAXPY assembly (RV32V)}
+
+\begin{semiverbatim}
+# a0 is n, a1 is ptr to x[0], a2 is ptr to y[0], fa0 is a
+ li t0, 2<<25
+ vsetdcfg t0            # enable 2 64b Fl.Pt. registers
+loop:
+ setvl  t0, a0          # vl = t0 = min(mvl, n)
+ vld    v0, a1          # load vector x
+ slli   t1, t0, 3       # t1 = vl * 8 (in bytes)
+ vld    v1, a2          # load vector y
+ add    a1, a1, t1      # increment pointer to x by vl*8
+ vfmadd v1, v0, fa0, v1 # v1 += v0 * fa0 (y = a * x + y)
+ sub    a0, a0, t0      # n -= vl (t0)
+ vst    v1, a2          # store Y
+ add    a2, a2, t1      # increment pointer to y by vl*8
+ bnez   a0, loop        # repeat if n != 0
+\end{semiverbatim}
+\end{frame}
+
+
+\begin{frame}[fragile]
+\frametitle{SV DAXPY assembly (RV64D)}
+
+\begin{semiverbatim}
+# a0 is n, a1 is ptr to x[0], a2 is ptr to y[0], fa0 is a
+ CSRvect1 = \{type: F, key: a3, val: a3, elwidth: dflt\}
+ CSRvect2 = \{type: F, key: a7, val: a7, elwidth: dflt\}
+loop:
+ setvl  t0, a0, 4       # vl = t0 = min(4, n)
+ ld     a3, a1          # load 4 registers a3-6 from x
+ slli   t1, t0, 3       # t1 = vl * 8 (in bytes)
+ ld     a7, a2          # load 4 registers a7-10 from y
+ add    a1, a1, t1      # increment pointer to x by vl*8
+ fmadd  a7, a3, fa0, a7 # v1 += v0 * fa0 (y = a * x + y)
+ sub    a0, a0, t0      # n -= vl (t0)
+ st     a7, a2          # store 4 registers a7-10 to y
+ add    a2, a2, t1      # increment pointer to y by vl*8
+ bnez   a0, loop        # repeat if n != 0
+\end{semiverbatim}
+\end{frame}
+
+
+\frame{\frametitle{Under consideration}
 
  \begin{itemize}
-   \item Designed for simplicity (graded levels of complexity)\vspace{10pt}
-   \item Fits RISC-V ethos: do more with less\vspace{10pt}
-   \item Reduces SIMD ISA proliferation by 3-4 orders of magnitude \\
-	     (without SIMD downsides or sacrificing speed trade-off)\vspace{10pt}
-   \item Covers 98\% of RVV, allows RVV to fit "on top"\vspace{10pt}
-   \item Huge range of implementor freedom and flexibility\vspace{10pt}
-   \item Not designed for supercomputing (that's RVV), designed for
-         in between: DSPs, RV32E, Embedded 3D GPUs etc.\vspace{10pt}
+   \item Is C.FNE actually needed? Should it be added if it is?
+   \item Element type implies polymorphism.  Should it be in SV?
+   \item Should use of registers be allowed to "wrap" (x30 x31 x1 x2)?
+   \item Is detection of all-scalar ops ok (without slowing pipeline)?
+   \item Can VSELECT be removed? (it's really complex)
+   \item Can CLIP be done as a CSR (mode, like elwidth)
+   \item SIMD saturation (etc.) also set as a mode?
+   \item Include src1/src2 predication on Comparison Ops?\\
+	     (same arrangement as C.MV, with same flexibility/power)
+   \item 8/16-bit ops is it worthwhile adding a "start offset"? \\
+         (a bit like misaligned addressing... for registers)\\
+         or just use predication to skip start?
   \end{itemize}
 }
 
 
-\frame{\frametitle{slide}
-
+\frame{\frametitle{What's the downside(s) of SV?}
  \begin{itemize}
-   \item \vspace{10pt}
-  \end{itemize}
-  Considerations:\vspace{10pt}
-  \begin{itemize}
-   \item \vspace{10pt}
+   \item EVERY register operation is inherently parallelised\\
+	     (scalar ops are just vectors of length 1)\vspace{4pt}
+   \item Tightly coupled with the core (instruction issue)\\
+         could be disabled through MISA switch\vspace{4pt}
+   \item An extra pipeline phase is pretty much essential\\
+         for fast low-latency implementations\vspace{4pt}
+   \item With zeroing off, skipping non-predicated elements is hard:\\
+         it is however an optimisation (and could be skipped).\vspace{4pt}
+   \item Setting up the Register/Predication tables (interpreting the\\
+	     CSR key-value stores) might be a bit complex to optimise
+	     (any change to a CSR key-value entry needs to redo the table)
   \end{itemize}
 }
 
 
-\frame{\frametitle{Including a plot}
+\frame{\frametitle{Is this OK (low latency)? Detect scalar-ops (only)}
  \begin{center}
-%  \includegraphics[height=2in]{dental.ps}\\
-  {\bf \red Dental trajectories for 27 children:}
+  \includegraphics[height=2.5in]{scalardetect.png}\\
+  {\bf \red Detect when all registers are scalar for a given op}
  \end{center}
 }
 
-\frame{\frametitle{Creating .pdf slides in WinEdt}
+
+\frame{\frametitle{Summary}
 
  \begin{itemize}
-   \item LaTeX [Shift-Control-L]\vspace{10pt}
-   \item dvi2pdf [click the button]\vspace{24pt}
-  \end{itemize}
-  To print 4 slides per page in acrobat click\vspace{10pt}
-   \begin{itemize}
-   \item File/print/properties\vspace{10pt}
-   \item Change ``pages per sheet'' to 4\vspace{10pt}
+   \item Actually about parallelism, not Vectors (or SIMD) per se
+   \item Only needs 3 actual instructions (plus CSRs)\\
+         RVV - and "standard" SIMD - require ISA duplication
+   \item Designed for flexibility (graded levels of complexity)
+   \item Huge range of implementor freedom
+   \item Fits RISC-V ethos: achieve more with less
+   \item Reduces SIMD ISA proliferation by 3-4 orders of magnitude \\
+	     (without SIMD downsides or sacrificing speed trade-off)
+   \item Covers 98\% of RVV, allows RVV to fit "on top"
+   \item Not designed for supercomputing (that's RVV), designed for
+         in between: DSPs, RV32E, Embedded 3D GPUs etc.
+   \item Not specifically designed for Vectorisation: designed to\\
+	     reduce code size (increase efficiency, just
+		 like Compressed)
   \end{itemize}
 }
 
+
 \frame{
   \begin{center}
-    {\Huge \red The end}
+    {\Huge \red The end\vspace{20pt}\\
+			    Thank you}
   \end{center}
 }