03bd5198b6
I have stumbled into this pretty accidentally, when rewriting some spaghetti-like code into something more structured, which involved using some `std::array<>`s. And to my surprise, the `alloca`s remained, causing about `+160%` perf regression. https://llvm-compile-time-tracker.com/compare.php?from=bb6f4d32aac3eecb51909f4facc625219307ee68&to=d563e66f40f9d4d145cb2050e41cb961e2b37785&stat=instructions suggests that this has geomean compile-time cost of `+0.08%`. Note that D68593 / cecc0d27ad58c0aed8ef9ed99bbf691e137a0f26 already did this chage for NewPM, but left OldPM in a pessimized state. This fixes [[ https://bugs.llvm.org/show_bug.cgi?id=40011 | PR40011 ]], [[ https://bugs.llvm.org/show_bug.cgi?id=42794 | PR42794 ]] and probably some other reports. Reviewed By: nikic, xbolva00 Differential Revision: https://reviews.llvm.org/D87972
46 lines
1.3 KiB
C++
46 lines
1.3 KiB
C++
// RUN: %clang_cc1 %s -O1 -std=c++11 -triple x86_64-unknown-linux-gnu -target-cpu x86-64 -target-feature +sse4.2 -target-feature +avx -emit-llvm -o - | FileCheck %s
|
|
|
|
// Testcase from llvm.org/PR32056
|
|
|
|
extern "C" int printf (const char *__restrict __format, ...);
|
|
|
|
typedef double __m256d __attribute__((__vector_size__(32)));
|
|
|
|
static __inline __m256d __attribute__((__always_inline__, __nodebug__,
|
|
__target__("avx")))
|
|
_mm256_setr_pd(double __a, double __b, double __c, double __d) {
|
|
return (__m256d){ __a, __b, __c, __d };
|
|
}
|
|
|
|
struct A {
|
|
A () {
|
|
// Check that the TBAA information generated for the stores to the
|
|
// union members is based on the omnipotent char.
|
|
// CHECK: store <4 x double>
|
|
// CHECK: tbaa ![[OCPATH:[0-9]+]]
|
|
// CHECK: store <4 x double>
|
|
// CHECK: tbaa ![[OCPATH]]
|
|
// CHECK: call
|
|
a = _mm256_setr_pd(0.0, 1.0, 2.0, 3.0);
|
|
b = _mm256_setr_pd(4.0, 5.0, 6.0, 7.0);
|
|
}
|
|
|
|
const double *begin() { return c; }
|
|
const double *end() { return c+8; }
|
|
|
|
union {
|
|
struct { __m256d a, b; };
|
|
double c[8];
|
|
};
|
|
};
|
|
|
|
int main(int argc, char *argv[]) {
|
|
A a;
|
|
for (double value : a)
|
|
printf("%f ", value);
|
|
return 0;
|
|
}
|
|
|
|
// CHECK-DAG: ![[CHAR:[0-9]+]] = !{!"omnipotent char"
|
|
// CHECK-DAG: ![[OCPATH]] = !{![[CHAR]], ![[CHAR]], i64 0}
|