add fmin/max and mark as high priority

diff --git a/openpower/sv/rfc/ls012/optable.csv b/openpower/sv/rfc/ls012/optable.csv
index 56503e7af4703990e54d6071c69b6827bc4c0037..60995249728e9573de7def3c563a04289035daa0 100644 (file)
--- a/openpower/sv/rfc/ls012/optable.csv
+++ b/openpower/sv/rfc/ls012/optable.csv
@@ -126,21 +126,21 @@ fpown(s),        TBD,   low,  10, yes, EXT2xx, no, transcendentals, 2R1W1w
 fpowr(s),        TBD,   low,  10, yes, EXT2xx, no, transcendentals, 2R1W1w
 frootn(s),       TBD,   low,  10, yes, EXT2xx, no, transcendentals, 2R1W1w
 fhypot(s),       TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminnum08(s),    TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxnum08(s),    TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmin19(s),       TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmax19(s),       TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminnum19(s),    TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxnum19(s),    TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminc(s),        TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxc(s),        TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminmagnum08(s), TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxmagnum08(s), TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminmag19(s),    TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxmag19(s),    TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminmagnum19(s), TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxmagnum19(s), TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fminmagc(s),     TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
-fmaxmagc(s),     TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
+fminnum08(s),    TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxnum08(s),    TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmin19(s),       TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmax19(s),       TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fminnum19(s),    TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxnum19(s),    TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fminc(s),        TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxc(s),        TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fminmagnum08(s), TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxmagnum08(s), TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fminmag19(s),    TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxmag19(s),    TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fminmagnum19(s), TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxmagnum19(s), TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fminmagc(s),     TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
+fmaxmagc(s),     TBD,   high, 10, yes, TBD,    no, transcendentals, 2R1W1w
 fmod(s),         TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w
 fremainder(s),   TBD,   TBD,  10, yes, TBD,    no, transcendentals, 2R1W1w

diff --git a/openpower/transcendentals.mdwn b/openpower/transcendentals.mdwn
index f4b7f14b694afa8fd81496480de5e4303cc450d1..38886535528278d172c67e6322a01021e4df0e19 100644 (file)
--- a/openpower/transcendentals.mdwn
+++ b/openpower/transcendentals.mdwn
@@ -42,6 +42,7 @@ TODO: rename extension subsets -- we're not on RISC-V anymore.
   acosh, atanh (can be synthesised - see below)
 * **ZftransAdv**: much more complex to implement in hardware
 * **Zfrsqrt**: Reciprocal square-root.
+* **Zfminmax**: Min/Max.
 
 Minimum recommended requirements for 3D: Zftrans, Ztrignpi,
 Zarctrignpi, with Ztrigpi and Zarctrigpi as augmentations.
@@ -233,22 +234,22 @@ Note (6) 4xf32-only, requires VMX.
 | fpowr        | x power of y (x +ve)                 | FRT = exp(FRA log(FRB))                        | ZftransAdv  |
 | frootn       | x power 1/n (n integer)              | FRT = pow(FRA, 1/RB)                           | ZftransAdv  |
 | fhypot       | hypotenuse                           | FRT = sqrt(FRA^2 + FRB^2)                      | ZftransAdv  |
-| fminnum08    | IEEE 754-2008 minNum                 | FRT = minNum(FRA, FRB)  (1)                    | TBD         |
-| fmaxnum08    | IEEE 754-2008 maxNum                 | FRT = maxNum(FRA, FRB)  (1)                    | TBD         |
-| fmin19       | IEEE 754-2019 minimum                | FRT = minimum(FRA, FRB)                        | TBD         |
-| fmax19       | IEEE 754-2019 maximum                | FRT = maximum(FRA, FRB)                        | TBD         |
-| fminnum19    | IEEE 754-2019 minimumNumber          | FRT = minimumNumber(FRA, FRB)                  | TBD         |
-| fmaxnum19    | IEEE 754-2019 maximumNumber          | FRT = maximumNumber(FRA, FRB)                  | TBD         |
-| fminc        | C ternary-op minimum                 | FRT = FRA \< FRB ? FRA : FRB                   | TBD         |
-| fmaxc        | C ternary-op maximum                 | FRT = FRA > FRB ? FRA : FRB                    | TBD         |
-| fminmagnum08 | IEEE 754-2008 minNumMag              | FRT = minmaxmag(FRA, FRB, False, fminnum08) (2)| TBD         |
-| fmaxmagnum08 | IEEE 754-2008 maxNumMag              | FRT = minmaxmag(FRA, FRB, True, fmaxnum08) (2) | TBD         |
-| fminmag19    | IEEE 754-2019 minimumMagnitude       | FRT = minmaxmag(FRA, FRB, False, fmin19) (2)   | TBD         |
-| fmaxmag19    | IEEE 754-2019 maximumMagnitude       | FRT = minmaxmag(FRA, FRB, True, fmax19) (2)    | TBD         |
-| fminmagnum19 | IEEE 754-2019 minimumMagnitudeNumber | FRT = minmaxmag(FRA, FRB, False, fminnum19) (2)| TBD         |
-| fmaxmagnum19 | IEEE 754-2019 maximumMagnitudeNumber | FRT = minmaxmag(FRA, FRB, True, fmaxnum19) (2) | TBD         |
-| fminmagc     | C ternary-op minimum magnitude       | FRT = minmaxmag(FRA, FRB, False, fminc) (2)    | TBD         |
-| fmaxmagc     | C ternary-op maximum magnitude       | FRT = minmaxmag(FRA, FRB, True, fmaxc) (2)     | TBD         |
+| fminnum08    | IEEE 754-2008 minNum                 | FRT = minNum(FRA, FRB)  (1)                    | Zfminmax    |
+| fmaxnum08    | IEEE 754-2008 maxNum                 | FRT = maxNum(FRA, FRB)  (1)                    | Zfminmax    |
+| fmin19       | IEEE 754-2019 minimum                | FRT = minimum(FRA, FRB)                        | Zfminmax    |
+| fmax19       | IEEE 754-2019 maximum                | FRT = maximum(FRA, FRB)                        | Zfminmax    |
+| fminnum19    | IEEE 754-2019 minimumNumber          | FRT = minimumNumber(FRA, FRB)                  | Zfminmax    |
+| fmaxnum19    | IEEE 754-2019 maximumNumber          | FRT = maximumNumber(FRA, FRB)                  | Zfminmax    |
+| fminc        | C ternary-op minimum                 | FRT = FRA \< FRB ? FRA : FRB                   | Zfminmax    |
+| fmaxc        | C ternary-op maximum                 | FRT = FRA > FRB ? FRA : FRB                    | Zfminmax    |
+| fminmagnum08 | IEEE 754-2008 minNumMag              | FRT = minmaxmag(FRA, FRB, False, fminnum08) (2)| Zfminmax    |
+| fmaxmagnum08 | IEEE 754-2008 maxNumMag              | FRT = minmaxmag(FRA, FRB, True, fmaxnum08) (2) | Zfminmax    |
+| fminmag19    | IEEE 754-2019 minimumMagnitude       | FRT = minmaxmag(FRA, FRB, False, fmin19) (2)   | Zfminmax    |
+| fmaxmag19    | IEEE 754-2019 maximumMagnitude       | FRT = minmaxmag(FRA, FRB, True, fmax19) (2)    | Zfminmax    |
+| fminmagnum19 | IEEE 754-2019 minimumMagnitudeNumber | FRT = minmaxmag(FRA, FRB, False, fminnum19) (2)| Zfminmax    |
+| fmaxmagnum19 | IEEE 754-2019 maximumMagnitudeNumber | FRT = minmaxmag(FRA, FRB, True, fmaxnum19) (2) | Zfminmax    |
+| fminmagc     | C ternary-op minimum magnitude       | FRT = minmaxmag(FRA, FRB, False, fminc) (2)    | Zfminmax    |
+| fmaxmagc     | C ternary-op maximum magnitude       | FRT = minmaxmag(FRA, FRB, True, fmaxc) (2)     | Zfminmax    |
 | fmod         | modulus                              | FRT = fmod(FRA, FRB)                           | TBD         |
 | fremainder   | IEEE 754 remainder                   | FRT = remainder(FRA, FRB)                      | TBD         |
 
@@ -327,6 +328,8 @@ the less common subsets are still required for IEEE754 HPC.
 MALI Midgard, an embedded / mobile 3D GPU, for example only has the
 following opcodes:
 
+    28 - fmin
+    2C - fmax
     E8 - fatan_pt2
     F0 - frcp (reciprocal)
     F2 - frsqrt (inverse square root, 1/sqrt(x))
@@ -343,6 +346,7 @@ Vivante Embedded/Mobile 3D (etnaviv
 <https://github.com/laanwj/etna_viv/blob/master/rnndb/isa.xml>) 
 only has the following:
 
+    fmin/fmax (implemented using SELECT)
     sin, cos2pi
     cos, sin2pi
     log2, exp
@@ -354,6 +358,7 @@ It also has fast variants of some of these, as a CSR Mode.
 AMD's R600 GPU (R600\_Instruction\_Set\_Architecture.pdf) and the
 RDNA ISA (RDNA\_Shader\_ISA\_5August2019.pdf, Table 22, Section 6.3) have:
 
+    MIN/MAX/MIN_DX10/MAX_DX10
     COS2PI (appx)
     EXP2
     LOG (IEEE754)
@@ -363,7 +368,7 @@ RDNA ISA (RDNA\_Shader\_ISA\_5August2019.pdf, Table 22, Section 6.3) have:
     SIN2PI (appx)
 
 AMD RDNA has F16 and F32 variants of all the above, and also has F64
-variants of SQRT, RSQRT and RECIP.  It is interesting that even the
+variants of SQRT, RSQRT, MIN, MAX, and RECIP.  It is interesting that even the
 modern high-end AMD GPU does not have TAN or ATAN, where MALI Midgard
 does.
 
@@ -482,6 +487,28 @@ is acceptable for 3D.
 
 Therefore they are their own subset extensions.
 
+### Zfminmax
+
+* fminnum08 fmaxnum08
+* fmin19 fmax19
+* fminnum19 fmaxnum19
+* fminc fmaxc
+* fminmagnum08 fmaxmagnum08
+* fminmag19 fmaxmag19
+* fminmagnum19 fmaxmagnum19
+* fminmagc fmaxmagc
+
+These are commonly used for vector reductions, where having them be a single
+instruction is critical. They are also commonly used in GPU shaders, HPC, and
+general-purpose FP algorithms.
+
+These min and max operations are quite cheap to implement hardware-wise,
+being comparable in cost to fcmp + some muxes. They're all in one extension
+because once you implement some of them, the rest require only slightly more
+hardware complexity.
+
+Therefore they are their own subset extension.
+
 # Synthesis, Pseudo-code ops and macro-ops
 
 The pseudo-ops are best left up to the compiler rather than being actual