The Shape of Code

How close is the agreement between the behavior of a compiler and its corresponding language specification?

In the previous century, some Standards’ bodies offered a compiler validation service. However, even when the number of commercial compilers numbered in the hundreds, this service was not commercially viable. These days there are only a handful of industrial strength compilers.

The availability of huge quantities of Open source, for some languages, has created a new language specification. Being able to turn much of this source into executable programs has become an effective measure of compiler correctness.

Those working on C/C++ compilers (Open source or otherwise), often claim that they implement the requirements contained in the corresponding ISO Standard. Some are active in the ISO Standards’ process, and I believe that they do strive to implement the requirements contained in the language standard.

How confident can we be that all the requirements contained in a language standard are correctly implemented by a compiler?

There is a cottage industry of testing compiler runtime behavior, often using fuzzers, and sometimes a compiler is one of the programs chosen to test new fuzzing techniques. This research checks optimization and code generation.

This runtime testing is all well and good, but a large percentage of the text in a language specification contains requirements on the syntax and semantics. The quality of syntax/semantic testing depends on how well the people writing the tests understand the language semantics. It takes a year or two of detailed study to achieve an effective compiler-level of understanding of these ‘front-end’ requirements.

The approach taken by the Model Implementation C Checker to show syntax/semantic correctness was to cross-referenced every if-statement in the front-end to one or more lines in the C90 Standard (the 1990 edition of the ISO C Standard), or an internal house-keeping reference (the source contained 3K references to 1.3K requirements in the C Standard). This compiler/checker was formally validated by BSI. As far as I know, this is the only compiler source cross-referenced at the level of individual lines/if-statements; there are compilers whose source contains cross-references to the sections of a language specification.

The main benefit of this cross-referencing process is insuring that every requirement in the C Standard is addressed by the compiler (correctly or otherwise). Other benefits include providing packets of wording for targeted tests and the ability to generate a runtime trace of all language features involved in compiling a given translation unit.

Replicating this cross-referencing for the gcc or llvm C compiler front-ends would be a huge amount of work for somebody who already has a detailed knowledge of the C Standard, along with some knowledge of compilers. The number of pages in the Standard relating to the C language has grown from 101 pages in C90 to 190 pages in C23. At an average of 14 cross-referenceable lines per page, the expected number of cross-references is now likely to be around 2,700.

LLMs are great at extracting information from text, can generate impressive quality C conformance tests, and are much, much cheaper than C language experts. How good are LLMs at working out which section(s)/paragraph(s) in the C Standard are implemented by the source code of a function contained in, say, gcc?

The LLM prompt I used to test out the idea was:

   List the section and paragraph number of the latest
   ISO C standard containing the requirements implemented
   in the following source code from a C compiler

Links to all responses from: ChatGPT5 Thinking, Grok3 Fast and Gok3 Expert.

It is very likely that text from the various versions of the C Standard were in the training data of the larger LLMs, so I did not include this material in the prompt. ChatGPT5 Thinking listed the 2024 draft N3220 as its source document.

The source code was copied from the C front-end code of gcc (i.e., the directory: gcc-15.1.0/gcc/c), which contains 67KLOC, with 6.8K if-statements.

Starting small, the following code looked like an easy test (I removed the comment containing text from the C Standard and obscured the big clue in the original function name: null_pointer_constant_p):

bool check_is_n_ptr (const_tree expr)
{
  /* This should really operate on c_expr structures, but they aren't
     yet available everywhere required.  */
  tree type = TREE_TYPE (expr);
 
  if (expr == nullptr_node)
    return true;
 
  return (TREE_CODE (expr) == INTEGER_CST
          && !TREE_OVERFLOW (expr)
          && integer_zerop (expr)
          && (INTEGRAL_TYPE_P (type)
              || (TREE_CODE (type) == POINTER_TYPE
                  && VOID_TYPE_P (TREE_TYPE (type))
                  && TYPE_QUALS (TREE_TYPE (type)) == TYPE_UNQUALIFIED)));
}

Wow, ChatGPT5 Thinking’s response even included a note on why the code checks for an unqualified type:

Here are the exact C23 (ISO/IEC 9899:2024) clauses that your function is implementing:

6.3.2.3 Pointers, ¶3 — Definition of a null pointer constant: “An integer constant expression
   with the value 0, such an expression cast to type void *, or the predefined constant nullptr
   is called a null pointer constant.”
6.6 Constant expressions, ¶8 — What qualifies as an integer constant expression
   (your INTEGER_CST / INTEGRAL_TYPE_P checks).
6.6 Constant expressions, ¶4 — Range requirement for constant expressions
   (motivates the !TREE_OVERFLOW (expr) check).
6.4.4.6 Predefined constants, ¶¶1–3 — nullptr is a predefined constant (token classification;
    ties to your expr == nullptr_node fast-path).
6.3.2.4 nullptr_t, ¶¶1–2 — Conversions of nullptr_t (confirms nullptr converts to any pointer
    type yielding the null pointer value).
Notes
  • The “cast to type void *” wording in 6.3.2.3 means unqualified void *,
    which is why your code insists the pointed-to void is unqualified.

Grok3 Fast’s response was even more expansive (and almost instantaneous), listing examples of section/paragraphs containing uses of null pointers, and pointing out that the wording was unchanged until C23 (when the nullptr keyword was introduced, along with its type nullptr_t). It also pointed out gcc specific features of the implementation (the prompt did not identify the compiler).

That’s enough of the easy questions. The following code (comments removed, function name unchanged) is essentially asking a question: What is the promoted type of the argument?

tree c_type_promotes_to (tree type)
{
  tree ret = NULL_TREE;
 
  if (TYPE_MAIN_VARIANT (type) == float_type_node)
    ret = double_type_node;
  else if (c_promoting_integer_type_p (type))
    {
      if (TYPE_UNSIGNED (type)
          && (TYPE_PRECISION (type) == TYPE_PRECISION (integer_type_node)))
        ret = unsigned_type_node;
      else
        ret = integer_type_node;
    }
 
  if (ret != NULL_TREE)
    return (TYPE_ATOMIC (type)
            ? c_build_qualified_type (ret, TYPE_QUAL_ATOMIC)
            : ret);
 
  return type;
}

ChatGPT5 listed six references. Three were good, and the other three were closely related, but I would not have cited them. The seven Grok3 references came from several documents using slightly different section numbers. Updating the prompt to explicitly name N3220 as the document to use did not change Grok3’s cited references (for this question).

All the code in the previous questions was there because of text in the C Standard. How do ChatGPT5/Grok3 handle the presence of code that does not have standard associated text?

The following function contains code to handle named address spaces (defined in a 2005 Technical Report: TR 18037 Extensions to support embedded processors).

static tree
qualify_type (tree type, tree like)
{
  addr_space_t as_type = TYPE_ADDR_SPACE (type);
  addr_space_t as_like = TYPE_ADDR_SPACE (like);
  addr_space_t as_common;
 
  /* If the two named address spaces are different, determine the common
     superset address space.  If there isn't one, raise an error.  */
  if (!addr_space_superset (as_type, as_like, &as_common))
    {
      as_common = as_type;
      error ("%qT and %qT are in disjoint named address spaces",
             type, like);
    }
 
  return c_build_qualified_type (type,
                        TYPE_QUALS_NO_ADDR_SPACE (type)
                        | TYPE_QUALS_NO_ADDR_SPACE_NO_ATOMIC (like)
                        | ENCODE_QUAL_ADDR_SPACE (as_common));
}

ChatGPT5 listed six good references and pointed out the association between the named address space code and TR 18037. Grok3 Fast hallucinated extensive quoted text/references from TR 18037 related to named address spaces. Grok3 Expert pointed out that the Standard does not contain any requirements related to named address spaces and listed two reasonable references.

Finding appropriate cross-references is the time-consuming first step. Next, I want the LLM to add them as comments next to the corresponding code.

I picked a 312 line function, and updated the prompt to add comments to the attached file:

   Find the section and paragraph numbers in the ISO C
   standard, specified in document N3220, containing the
   requirements implemented in the source code contained
   in the attached file, and add these section and paragraph
   numbers at the corresponding places in the code as comment

ChatGPT5 Thinking thought for 5 min 46 secs (output), and Grok3 Expert thought for 3 mins 4 secs (output).

Both ChatGPT5 and Grok3 modified the existing code, either by joining adjacent lines, changing variable names, or deleting lines. ChatGPT made far fewer changes, while the Grok3 output was 65 lines shorter than the original (including the added comments).

Both LLMs added comments to blocks of if-statements (my fault for not explicitly specifying that every if should be cross-referenced), with ChatGPT5 adding the most cross-references.

One way to stop the LLMs making unasked for changes to the source is to have them focus on the added comments, i.e., ask for a diff that can be fed into patch. The updated prompt is:

   Find the section and paragraph numbers in the ISO C
   standard, specified in document N3220, containing the
   requirements implemented by each if statement in the
   source code contained in the attached file.  Create a
   diff file that patch can use to add these section and
   paragraph numbers as comments at the corresponding lines
   in the original code

ChatGPT5 Thinking thought for around 4 min (it reported inconsistent values (output), and Grok3 Expert thought for 5 min 1 sec (output).

The ChatGPT5 patch contained many more cross-references than its earlier output, with comments on more if-statements. The Grok3 patch was a third the size of the ChatGPT5 patch.

How well did the LLMs perform?

ChatGPT5 did very well, and its patch output would be a good starting point for a detailed human expert edit. Perhaps an improved prompt, or some form of fine-tuning would useful improve performance.

Grok3 Fast does not appear to be usable, but Grok3 Expert could be used as an independent check against ChatGPT5 output.

Working at the section/paragraph level it is not always possible to give the necessary detailed cross-reference because some paragraphs contain multiple requirements. It might be easier to split the C Standard text into smaller chunks, rather than trying to get LLMs to give line offsets within a paragraph.