; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t1 --use-offset=0 --show-density -profile-density-threshold=10  --trim-cold-profile=0 &> %t2
; RUN: FileCheck %s --input-file %t2 --check-prefix=CHECK-DENSITY
; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density-cs.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t3 --show-density -profile-density-threshold=1 -profile-density-threshold=10000 &> %t4
; RUN: FileCheck %s --input-file %t4 --check-prefix=CHECK-DENSITY-CS
; RUN: llvm-profgen --format=text --unsymbolized-profile=%S/Inputs/profile-density-cs.raw.prof --binary=%S/Inputs/inline-noprobe2.perfbin --output=%t5 --show-density -profile-density-threshold=1 -profile-density-cutoff-hot=800000  &> %t6
; RUN: FileCheck %s --input-file %t6 --check-prefix=CHECK-DENSITY-CS-80

;CHECK-DENSITY: Sample PGO is estimated to optimize better with 2.9x more samples. Please consider increasing sampling rate or profiling for longer duration to get more samples.
;CHECK-DENSITY: Functions with density >= 3.5 account for 99.00% total sample counts.

;CHECK-DENSITY-CS: Sample PGO is estimated to optimize better with 12.5x more samples. Please consider increasing sampling rate or profiling for longer duration to get more samples.
;CHECK-DENSITY-CS: Functions with density >= 800.1 account for 99.00% total sample counts.

;CHECK-DENSITY-CS-80: Functions with density >= 1886.2 account for 80.00% total sample counts.

; original code:
; clang -O3 -g -fno-optimize-sibling-calls -fdebug-info-for-profiling qsort.c -o a.out
#include <stdio.h>
#include <stdlib.h>

void swap(int *a, int *b) {
	int t = *a;
	*a = *b;
	*b = t;
}

int partition_pivot_last(int* array, int low, int high) {
	int pivot = array[high];
	int i = low - 1;
	for (int j = low; j < high; j++)
		if (array[j] < pivot)
			swap(&array[++i], &array[j]);
	swap(&array[i + 1], &array[high]);
	return (i + 1);
}

int partition_pivot_first(int* array, int low, int high) {
	int pivot = array[low];
	int i = low + 1;
	for (int j = low + 1; j <= high; j++)
		if (array[j] < pivot) { if (j != i) swap(&array[i], &array[j]); i++;}
	swap(&array[i - 1], &array[low]);
	return i - 1;
}

void quick_sort(int* array, int low, int high, int (*partition_func)(int *, int, int)) {
	if (low < high) {
		int pi = (*partition_func)(array, low, high);
		quick_sort(array, low, pi - 1, partition_func);
		quick_sort(array, pi + 1, high, partition_func);
	}
}

int main() {
	const int size = 200;
	int sum = 0;
	int *array = malloc(size * sizeof(int));
	for(int i = 0; i < 100 * 1000; i++) {
		for(int j = 0; j < size; j++)
			array[j] = j % 10 ? rand() % size: j;
		int (*fptr)(int *, int, int) = i % 3 ? partition_pivot_last : partition_pivot_first;
		quick_sort(array, 0, size - 1, fptr);
		sum += array[i % size];
	}
	printf("sum=%d\n", sum);

	return 0;
}