#include <stdbool.h>
#include <stdint.h>

static inline uint64_t saturating_sub_u64(uint64_t a, uint64_t b) {
    return a > b ? a - b : 0;
}

uint32_t test1a(uint32_t a, uint32_t b) {
    return a > b ? a - b : 0;
}

uint32_t test1b(uint32_t a, uint32_t b) {
    return (uint64_t)a > (uint64_t)b ? (uint64_t)a - (uint64_t)b : (uint64_t)0;
}

uint32_t test1c(uint32_t a, uint32_t b) {
    return saturating_sub_u64(a, b);
}

Expected result: test1a, test1b and test1c functions transform to same code.

Actual result: test1a and test1b transform to same code, but test1c produces slightly larger code, with unnecessary zero extension operations.

This can be tested in Compiler Explorer.

x86-64 clang 19.1.0 with -Os option produces:

test1b:
        xorl    %eax, %eax
        subl    %esi, %edi
        cmovael %edi, %eax
        retq

test1c:
        movl    %edi, %ecx
        movl    %esi, %edx
        xorl    %eax, %eax
        subq    %rdx, %rcx
        cmovaeq %rcx, %rax
        retq

Related: GCC bug 118679
When I reported the bug in GCC, I have another example that GCC missed the optimization for, but somehow Clang optimized it correctly (see the max_u64 and test2 functions in that bug report). The saturating_sub_u64 case is what Clang missed.