+[[!tag oldstandards]]
+
MV.X and MV.swizzle
===================
-swizzle needs a MV. see below for a potential way to use the funct7 to do a swizzle in rs2.
+swizzle needs a MV (there are 2 of them: swizzle and swizzle2).
+see below for a potential way to use the funct7 to do a swizzle in rs2.
+---------------+-------------+-------+----------+----------+--------+----------+--------+--------+
| Encoding | 31:27 | 26:25 | 24:20 | 19:15 | 14:12 | 11:7 | 6:2 | 1:0 |
question: do we need a swizzle MV.X as well?
+MV.X with 3 operands
+====================
+
+regs[rd] = regs[rs1 + regs[rs2]]
+
+Similar to LD/ST with the same twin predication rules
+
macro-op fusion
===============
I3 = _mm_unpackhi_epi64(T2, T3);
Transforms for DCT
-=======
+==================
+
<https://opencores.org/websvn/filedetails?repname=mpeg2fpga&path=%2Fmpeg2fpga%2Ftrunk%2Frtl%2Fmpeg2%2Fidct.v>
+Table to evaluate
+=================
+
+swizzle2 takes 2 arguments, interleaving the two vectors depending on a 3rd (the swizzle selector)
+
++-----------+-------+-------+-------+-------+-------+------+
+| | 31:27 | 26:25 | 24:20 | 19:15 | 14:12 | 11:7 |
++===========+=======+=======+=======+=======+=======+======+
+| swizzle2 | rs3 | 00 | rs2 | rs1 | 000 | rd |
++-----------+-------+-------+-------+-------+-------+------+
+| fswizzle2 | rs3 | 01 | rs2 | rs1 | 000 | rd |
++-----------+-------+-------+-------+-------+-------+------+
+| swizzle | 0 | 10 | rs2 | rs1 | 000 | rd |
++-----------+-------+-------+-------+-------+-------+------+
+| fswizzle | 0 | 11 | rs2 | rs1 | 000 | rd |
++-----------+-------+-------+-------+-------+-------+------+
+| swizzlei | imm | rs1 | 001 | rd |
++-----------+ +-------+-------+------+
+| fswizzlei | | rs1 | 010 | rd |
++-----------+-------+-------+-------+-------+-------+------+
+
+More:
+
+swizzlei would still need the 12-bit format due to not having enough immediate bits. we can get away with only 3 i-type funct3s used for [f]swizzlei by having one funct3 for destsubvl 1 through 3 for int and fp versions and a separate one for destsubvl = 4 that's shared between int/fp:
+
++--------+-----------+----+-----------+----------+-------+-------+------+
+| int/fp | DESTSUBVL | 31 | 30:29 | 28:20 | 19:15 | 14:12 | 11:7 |
++========+===========+====+===========+==========+=======+=======+======+
+| int | 1 to 3 | 0 | DESTSUBVL | selector | rs | 000 | rd |
++--------+-----------+----+-----------+----------+-------+-------+------+
+| fp | 1 to 3 | 1 | DESTSUBVL | selector | rs | 000 | rd |
++--------+-----------+----+-----------+----------+-------+-------+------+
+| int | 4 | selector[11:0] | rs | 001 | rd |
++--------+-----------+---------------------------+-------+-------+------+
+| fp | 4 | selector[11:0] | rs | 010 | rd |
++--------+-----------+---------------------------+-------+-------+------+
+
+the rest could be encoded as follows:
+
++-----------+-------+-----------+-------+-------+-------+------+
+| | 31:27 | 26:25 | 24:20 | 19:15 | 14:12 | 11:7 |
++===========+=======+===========+=======+=======+=======+======+
+| swizzle2 | rs3 | DESTSUBVL | rs2 | rs1 | 100 | rd |
++-----------+-------+-----------+-------+-------+-------+------+
+| swizzle | rs1 | DESTSUBVL | rs2 | rs1 | 100 | rd |
++-----------+-------+-----------+-------+-------+-------+------+
+| fswizzle2 | rs3 | DESTSUBVL | rs2 | rs1 | 101 | rd |
++-----------+-------+-----------+-------+-------+-------+------+
+| fswizzle | rs1 | DESTSUBVL | rs2 | rs1 | 101 | rd |
++-----------+-------+-----------+-------+-------+-------+------+
+
+note how for [f]swizzle, rs3 == rs1
+
+so it uses 5 funct3 values overall, which is appropriate, since swizzle is probably right after muladd in usage in graphics shaders.
+
+Alternative immed encoding
+
++--------+-----------+----------+-------+-------+------+
+| int/fp | 31:28 | 27:20 | 19:15 | 14:12 | 11:7 |
++========+===========+==========+=======+=======+======+
+| int | DESTMASK | selector | rs | 000 | rd |
++--------+-----------+----------+-------+-------+------+
+| fp | DESTMASK | selector | rs | 001 | rd |
++--------+-----------+----------+-------+-------+------+
+| int | DESTMASK | constsel | rs | 010 | rd |
++--------+-----------+----------+-------+-------+------+
+| fp | DESTMASK | constsel | rs | 011 | rd |
++--------+-----------+----------+-------+-------+------+
+
+Allows setting of arbitrary dest (xz, yw) without needing register-versions. Saves on instruction count.
+Needs 4 funct3 to express.
+
+Matrix 4x4 Vector mul
+=====================
+
+::
+
+ pfscale,3 F2, F1, F10
+ pfscaleadd,2 F2, F1, F11, F2
+ pfscaleadd,1 F2, F1, F12, F2
+ pfscaleadd,0 F2, F1, F13, F2
+
+pfscale is a 4 vec mv.shuffle followed by a fmul. pfscaleadd is a 4 vec mv.shuffle followed by a fmac.
+
+In effect what this is doing is:
+
+::
+
+ fmul f2, f1.xxxx, f10
+ fmac f2, f1.yyyy, f11, f2
+ fmac f2, f1.zzzz, f12, f2
+ fmac f2, f1.wwww, f13, f2
+
+Where all of f2, f1, and f10-13 are vec4, and f1.x-w are copied (fixed index) where the other vec4 indices progress.
+
+Pseudocode
+==========
+
+Swizzle:
+
+::
+
+ pub trait SwizzleConstants: Copy + 'static {
+ const CONSTANTS: &'static [Self; 4];
+ }
+
+ impl SwizzleConstants for u8 {
+ const CONSTANTS: &'static [Self; 4] = &[0, 1, 0xFF, 0x7F];
+ }
+
+ impl SwizzleConstants for u16 {
+ const CONSTANTS: &'static [Self; 4] = &[0, 1, 0xFFFF, 0x7FFF];
+ }
+
+ impl SwizzleConstants for f32 {
+ const CONSTANTS: &'static [Self; 4] = &[0.0, 1.0, -1.0, 0.5];
+ }
+
+ // impl for other types too...
+
+ pub fn swizzle<Elm, Selector>(
+ rd: &mut [Elm],
+ rs1: &[Elm],
+ rs2: &[Selector],
+ vl: usize,
+ destsubvl: usize,
+ srcsubvl: usize)
+ where
+ Elm: SwizzleConstants,
+ // Selector is a copyable type that can be converted into u64
+ Selector: Copy + Into<u64>,
+ {
+ const FIELD_SIZE: usize = 3;
+ const FIELD_MASK: u64 = 0b111;
+ for vindex in 0..vl {
+ let selector = rs2[vindex].into();
+ // selector's type is u64
+ if selector >> (FIELD_SIZE * destsubvl) != 0 {
+ // handle illegal instruction trap
+ }
+ for i in 0..destsubvl {
+ let mut sel_field = selector >> (FIELD_SIZE * i);
+ sel_field &= FIELD_MASK;
+ let src = if (sel_field & 0b100) == 0 {
+ &rs1[(vindex * srcsubvl)..]
+ } else {
+ SwizzleConstants::CONSTANTS
+ };
+ sel_field &= 0b11;
+ if sel_field as usize >= srcsubvl {
+ // handle illegal instruction trap
+ }
+ let value = src[sel_field as usize];
+ rd[vindex * destsubvl + i] = value;
+ }
+ }
+ }
+
+Swizzle2:
+
+::
+
+ fn swizzle2<Elm, Selector>(
+ rd: &mut [Elm],
+ rs1: &[Elm],
+ rs2: &[Selector],
+ rs3: &[Elm],
+ vl: usize,
+ destsubvl: usize,
+ srcsubvl: usize)
+ where
+ // Elm is a copyable type
+ Elm: Copy,
+ // Selector is a copyable type that can be converted into u64
+ Selector: Copy + Into<u64>,
+ {
+ const FIELD_SIZE: usize = 3;
+ const FIELD_MASK: u64 = 0b111;
+ for vindex in 0..vl {
+ let selector = rs2[vindex].into();
+ // selector's type is u64
+ if selector >> (FIELD_SIZE * destsubvl) != 0 {
+ // handle illegal instruction trap
+ }
+ for i in 0..destsubvl {
+ let mut sel_field = selector >> (FIELD_SIZE * i);
+ sel_field &= FIELD_MASK;
+ let src = if (sel_field & 0b100) != 0 {
+ rs1
+ } else {
+ rs3
+ };
+ sel_field &= 0b11;
+ if sel_field as usize >= srcsubvl {
+ // handle illegal instruction trap
+ }
+ let value = src[vindex * srcsubvl + (sel_field as usize)];
+ rd[vindex * destsubvl + i] = value;
+ }
+ }
+ }
+