[PATCH] D105020: [SLP]Improve graph reordering.

[Alexey Bataev via Phabricator via llvm-commits]

ABataev added a comment.

In D105020#2975046 <https://reviews.llvm.org/D105020#2975046>, @goncharov wrote:

> Here is a repro I found
>
>   $ cat ./repro.cc
>   #include <iostream>
>   namespace a {
>   __attribute__((noinline)) void b(uint8_t *c, float *d, uint16_t e, uint16_t f) {
>     uint16_t g = f;
>     uint16_t h = c[0] << 2 | c[4] & 3;
>     uint16_t l = c[1] << 2 | c[4] >> 2 & 3;
>     uint16_t v = c[2] << 2 | 3;
>     uint16_t j = c[3] << 2 | c[4] >> 6;
>     *(d - 1) = float(l - e) / g;
>     *(d - 2) = float(h - e) / g;
>     *(d - 3) = float(j - e) / g;
>     *(d - 4) = float(v - e) / g;
>   }
>   void bar(uint8_t *buffer, size_t k, size_t height, size_t, uint16_t e,
>            uint16_t f, float *m) {
>     int n = 24, g = f;
>     float *t = &m[(24 - 2) * 4];
>     size_t u = 2 * k;
>     for (int o; o < height; o++) {
>       uint8_t *p = buffer;
>       uint8_t *q = p;
>       float *r = &t[u];
>       for (int a = 0; a < u; a += 4) {
>         b(q, r, e, g);
>         r -= 4;
>       }
>       t -= n;
>     }
>   }
>   }  // namespace a
>   int main() {
>     uint8_t s[]{255, 0, 255, 0, 51};
>     float m[4 * 24]{};
>     a::bar(s, 4, 4, 0, 0, 1023, m);
>     int *out = reinterpret_cast<int *>(m);
>     int64_t sum;
>     for (int i = 0; i < sizeof(m) / sizeof(int); i++) sum += out[i];
>     std::cout << sum;
>   }
>   $ clang-before -O2 -std=gnu++17 repro.cc
>   $ ./a.out
>   17045651456
>   $ clang-after -O2 -std=gnu++17 repro.cc
>   $ ./a.out
>   16609148640

Thanks, this will help a lot!


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D105020/new/

https://reviews.llvm.org/D105020