Enable bf16x3, bf16x6 for dot input precisions (#5403)

Fixes #5364.
Enables two new precision types (bf16x3, bf16x6) for dot inputs.

Author: dev-tomek

python/test/unit/language/test_core.py

@@ -3272,8 +3272,6 @@ def test_dot(M, N, K, num_warps, col_a, col_b, epilogue, input_precision, in_dty
             pytest.xfail(f"input_precision {input_precision} is not supported in the interpreter")
     else:
         if is_xpu():
-            if input_precision in ("bf16x3", "bf16x6"):
-                pytest.skip(f"input_precision {input_precision} is not supported")
             if (M < 8 or N < 16 or (K < 16 and in_dtype == 'float16') or (K < 8 and in_dtype == 'float32')):
                 pytest.xfail("XPU: small dots are not supported")
         elif not is_hip() and K < 16:

third_party/intel/backend/compiler.py

@@ -30,7 +30,7 @@ class XPUOptions:
     supported_fp8_dtypes: Tuple[str] = ("fp8e5", "fp8e4nv", "fp8e4b15")
     deprecated_fp8_dot_operand_dtypes: Tuple[str] = ()
     default_dot_input_precision: str = "tf32"
-    allowed_dot_input_precisions: Tuple[str] = ("tf32", "tf32x3", "ieee")
+    allowed_dot_input_precisions: Tuple[str] = ("tf32", "tf32x3", "ieee", 'bf16x3', 'bf16x6')
     allow_fp8e4nv: bool = False
     allow_fp8e4b15: bool = True
     grf_mode: tuple = ('small', 'large', 'auto', 'default')