flip mx scaling enum default to RCEIL

Summary:

Overall we know RCEIL is better from industry knowledge, the benchmarks
below are very light just to validate we can measure the increase.

Accuracy
* before

```
wikitext: {'alias': 'wikitext', 'word_perplexity,none':
7.609070006132819, 'word_perplexity_stderr,none': 'N/A',
'byte_perplexity,none': 1.4615491037668933,
'byte_perplexity_stderr,none': 'N/A', 'bits_per_byte,none':
0.5474983002838458, 'bits_per_byte_stderr,none': 'N/A'}
winogrande: {'alias': 'winogrande', 'acc,none': 0.7292817679558011,
'acc_stderr,none': 0.012487904760626407}
```

* after

```
wikitext: {'alias': 'wikitext', 'word_perplexity,none':
7.605192917647689, 'word_perplexity_stderr,none': 'N/A',
'byte_perplexity,none': 1.4614098103053235,
'byte_perplexity_stderr,none': 'N/A', 'bits_per_byte,none':
0.547360797163005, 'bits_per_byte_stderr,none': 'N/A'}
winogrande: {'alias': 'winogrande', 'acc,none': 0.7355958958168903,
'acc_stderr,none': 0.012394724896983764}
```

nice lift in perplexity and winogrande accuracy score

Performance on norm -> linear benchmarks

* before: https://gist.github.com/vkuzo/e4eab53fc9a23c007585c2235a7c7088
* after: https://gist.github.com/vkuzo/4ac7cde8a3ec1cd8f4d66847df091f7e

a slight performance regression, but we have not optimized RCEIL
performance at all and we aren't using the intrinsics yet, so room to
optimize

Test Plan:

```
pytest test/prototype/mx_formats/ -s -x
```

Reviewers:

Subscribers:

Tasks:

Tags:
ghstack-source-id: f47b33f
ghstack-comment-id: 3608933956
Pull-Request: #3428

Author: vkuzo

torchao/prototype/mx_formats/README.md

@@ -230,7 +230,7 @@ Note: the accuracy results below are WIP and are not optimized yet.
 | recipe | wikitext word_perplexity | winogrande |
 | ------ | -------- | ---------- |
 | bfloat16 (baseline) | 7.5472105433748435 | 0.7426992896606156 |
-| mxfp8 | 7.609070006132819 | 0.7292817679558011 |
+| mxfp8 | 7.605192917647689 | 0.7355958958168903 |
 | nvfp4 | 8.44478255417328 | 0.7182320441988951 |
 
 To reproduce:

torchao/prototype/mx_formats/mx_tensor.py

@@ -87,7 +87,7 @@
 class QuantizeTensorToMXKwargs(QuantizeTensorKwargs):
     elem_dtype: Union[torch.dtype, str] = torch.float8_e4m3fn
     block_size: int = 32
-    scaling_mode: ScaleCalculationMode = ScaleCalculationMode.FLOOR
+    scaling_mode: ScaleCalculationMode = ScaleCalculationMode.RCEIL
     kernel_preference: KernelPreference = KernelPreference.EMULATED
     is_swizzled_scales: bool = False
 
@@ -144,7 +144,7 @@ def to_mx(
     data_hp: torch.Tensor,
     elem_dtype: Union[torch.dtype, str],
     block_size: int,
-    scaling_mode: ScaleCalculationMode = ScaleCalculationMode.FLOOR,
+    scaling_mode: ScaleCalculationMode = ScaleCalculationMode.RCEIL,
     is_swizzled_scales: bool = False,
 ):
     """
@@ -533,7 +533,7 @@ def to_mx(
         data_hp: torch.Tensor,
         elem_dtype: Union[torch.dtype, str],
         block_size: int = BLOCK_SIZE_DEFAULT,
-        scaling_mode: ScaleCalculationMode = ScaleCalculationMode.FLOOR,
+        scaling_mode: ScaleCalculationMode = ScaleCalculationMode.RCEIL,
         # TODO(future PR): switch default gemm to cublas
         kernel_preference: KernelPreference = KernelPreference.EMULATED,
         act_quant_kwargs: Optional[QuantizeTensorToMXKwargs] = None,