Initial FP8 support

Adds support for Open Compute Project (OCP) 8-bit floating point operations
to the TOSA specification. Both E4M3 and E5M2 types are supported for profiles
as indicated in the Supported Data Types table for each operator.

FP8 operator list
ARGMAX
AVGPOOL
CONV2D
CONV3D
DEPTHWISE_CONV2D
MATMUL
MAX_POOL2D
TRANSPOSE_CONV2D
CONST
CAST
CONCAT
PAD
DIM
RESHAPE
REVERSE
SLICE
TILE
TRANSPOSE
GATHER
SCATTER

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I3dd83f48afcc3c880c5c88039337ff4f1fd95b1b

1 files changed, 3 insertions, 6 deletions

diff --git a/pseudocode/library/type_conversion_helpers.tosac b/pseudocode/library/type_conversion_helpers.tosac
index f26c589..f2b42a6 100644
--- a/pseudocode/library/type_conversion_helpers.tosac
+++ b/pseudocode/library/type_conversion_helpers.tosac
@@ -11,6 +11,9 @@
 // A no-op for floating-point types
 Type make_signed(Type in_t)
 {
+    if (is_floating_point<in_t>()) {
+        return in_t;
+    }
     switch(in_t) {
         case bool_t:
             return bool_t;
@@ -22,12 +25,6 @@ Type make_signed(Type in_t)
             return int32_t;
         case i48_t:
             return int48_t;
-        case fp16_t:
-            return fp16_t;
-        case bf16_t:
-            return bf16_t;
-        case fp32_t:
-            return fp32_t;
     }
 }