diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 2656822..cefc715 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -23,6 +23,9 @@
 #include "util/time-utils.h"
 #include "util/annotate.h"
 #include "util/map.h"
+#include "util/spark.h"
+#include "util/block-info.h"
+#include "util/stream.h"
 #include <linux/err.h>
 #include <linux/zalloc.h>
 #include <subcmd/pager.h>
@@ -40,6 +43,7 @@
 	int				 range_size;
 	int				 range_num;
 	bool				 has_br_stack;
+	bool				 stream;
 };
 
 /* Diff command specific HPP columns. */
@@ -53,6 +57,7 @@
 	PERF_HPP_DIFF__FORMULA,
 	PERF_HPP_DIFF__DELTA_ABS,
 	PERF_HPP_DIFF__CYCLES,
+	PERF_HPP_DIFF__CYCLES_HIST,
 
 	PERF_HPP_DIFF__MAX_INDEX
 };
@@ -69,6 +74,7 @@
 	struct perf_data	 data;
 	int			 idx;
 	struct hists		*hists;
+	struct evlist_streams	*evlist_streams;
 	struct diff_hpp_fmt	 fmt[PERF_HPP_DIFF__MAX_INDEX];
 };
 
@@ -87,6 +93,7 @@
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
+static bool cycles_hist;
 static unsigned int sort_compute = 1;
 
 static s64 compute_wdiff_w1;
@@ -95,8 +102,6 @@
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
-static struct addr_location dummy_al;
-
 enum {
 	COMPUTE_DELTA,
 	COMPUTE_RATIO,
@@ -104,6 +109,7 @@
 	COMPUTE_DELTA_ABS,
 	COMPUTE_CYCLES,
 	COMPUTE_MAX,
+	COMPUTE_STREAM,	/* After COMPUTE_MAX to avoid use current compute arrays */
 };
 
 const char *compute_names[COMPUTE_MAX] = {
@@ -164,6 +170,10 @@
 	[PERF_HPP_DIFF__CYCLES] = {
 		.name  = "[Program Block Range] Cycles Diff",
 		.width = 70,
+	},
+	[PERF_HPP_DIFF__CYCLES_HIST] = {
+		.name  = "stddev/Hist",
+		.width = NUM_SPARKS + 9,
 	}
 };
 
@@ -387,6 +397,11 @@
 	struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool);
 	struct addr_location al;
 	struct hists *hists = evsel__hists(evsel);
+	struct hist_entry_iter iter = {
+		.evsel	= evsel,
+		.sample	= sample,
+		.ops	= &hist_iter_normal,
+	};
 	int ret = -1;
 
 	if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num,
@@ -405,14 +420,8 @@
 		goto out_put;
 	}
 
-	if (compute != COMPUTE_CYCLES) {
-		if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
-				      true)) {
-			pr_warning("problem incrementing symbol period, "
-				   "skipping event\n");
-			goto out_put;
-		}
-	} else {
+	switch (compute) {
+	case COMPUTE_CYCLES:
 		if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
 					  NULL, NULL, sample, true)) {
 			pr_warning("problem incrementing symbol period, "
@@ -420,7 +429,25 @@
 			goto out_put;
 		}
 
-		hist__account_cycles(sample->branch_stack, &al, sample, false);
+		hist__account_cycles(sample->branch_stack, &al, sample, false,
+				     NULL);
+		break;
+
+	case COMPUTE_STREAM:
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL)) {
+			pr_debug("problem adding hist entry, skipping event\n");
+			goto out_put;
+		}
+		break;
+
+	default:
+		if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
+				      true)) {
+			pr_warning("problem incrementing symbol period, "
+				   "skipping event\n");
+			goto out_put;
+		}
 	}
 
 	/*
@@ -448,6 +475,7 @@
 		.fork	= perf_event__process_fork,
 		.lost	= perf_event__process_lost,
 		.namespaces = perf_event__process_namespaces,
+		.cgroup = perf_event__process_cgroup,
 		.ordered_events = true,
 		.ordering_requires_timestamps = true,
 	},
@@ -459,7 +487,7 @@
 	struct evsel *e;
 
 	evlist__for_each_entry(evlist, e) {
-		if (perf_evsel__match2(evsel, e))
+		if (evsel__match2(evsel, e))
 			return e;
 	}
 
@@ -530,41 +558,6 @@
 	}
 }
 
-static int64_t block_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
-			 struct hist_entry *left, struct hist_entry *right)
-{
-	struct block_info *bi_l = left->block_info;
-	struct block_info *bi_r = right->block_info;
-	int cmp;
-
-	if (!bi_l->sym || !bi_r->sym) {
-		if (!bi_l->sym && !bi_r->sym)
-			return 0;
-		else if (!bi_l->sym)
-			return -1;
-		else
-			return 1;
-	}
-
-	if (bi_l->sym == bi_r->sym) {
-		if (bi_l->start == bi_r->start) {
-			if (bi_l->end == bi_r->end)
-				return 0;
-			else
-				return (int64_t)(bi_r->end - bi_l->end);
-		} else
-			return (int64_t)(bi_r->start - bi_l->start);
-	} else {
-		cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
-		return cmp;
-	}
-
-	if (bi_l->sym->start != bi_r->sym->start)
-		return (int64_t)(bi_r->sym->start - bi_l->sym->start);
-
-	return (int64_t)(bi_r->sym->end - bi_l->sym->end);
-}
-
 static int64_t block_cycles_diff_cmp(struct hist_entry *left,
 				     struct hist_entry *right)
 {
@@ -593,87 +586,19 @@
 
 	INIT_LIST_HEAD(&bh->block_fmt.list);
 	INIT_LIST_HEAD(&bh->block_fmt.sort_list);
-	bh->block_fmt.cmp = block_cmp;
+	bh->block_fmt.cmp = block_info__cmp;
 	bh->block_fmt.sort = block_sort;
 	perf_hpp_list__register_sort_field(&bh->block_list,
 					   &bh->block_fmt);
 	bh->valid = true;
 }
 
-static void init_block_info(struct block_info *bi, struct symbol *sym,
-			    struct cyc_hist *ch, int offset)
-{
-	bi->sym = sym;
-	bi->start = ch->start;
-	bi->end = offset;
-	bi->cycles = ch->cycles;
-	bi->cycles_aggr = ch->cycles_aggr;
-	bi->num = ch->num;
-	bi->num_aggr = ch->num_aggr;
-}
-
-static int process_block_per_sym(struct hist_entry *he)
-{
-	struct annotation *notes;
-	struct cyc_hist *ch;
-	struct block_hist *bh;
-
-	if (!he->ms.map || !he->ms.sym)
-		return 0;
-
-	notes = symbol__annotation(he->ms.sym);
-	if (!notes || !notes->src || !notes->src->cycles_hist)
-		return 0;
-
-	bh = container_of(he, struct block_hist, he);
-	init_block_hist(bh);
-
-	ch = notes->src->cycles_hist;
-	for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
-		if (ch[i].num_aggr) {
-			struct block_info *bi;
-			struct hist_entry *he_block;
-
-			bi = block_info__new();
-			if (!bi)
-				return -1;
-
-			init_block_info(bi, he->ms.sym, &ch[i], i);
-			he_block = hists__add_entry_block(&bh->block_hists,
-							  &dummy_al, bi);
-			if (!he_block) {
-				block_info__put(bi);
-				return -1;
-			}
-		}
-	}
-
-	return 0;
-}
-
-static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
-{
-	struct block_info *bi_a = a->block_info;
-	struct block_info *bi_b = b->block_info;
-	int cmp;
-
-	if (!bi_a->sym || !bi_b->sym)
-		return -1;
-
-	cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
-
-	if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
-		return 0;
-
-	return -1;
-}
-
 static struct hist_entry *get_block_pair(struct hist_entry *he,
 					 struct hists *hists_pair)
 {
 	struct rb_root_cached *root = hists_pair->entries_in;
 	struct rb_node *next = rb_first_cached(root);
-	int cmp;
+	int64_t cmp;
 
 	while (next != NULL) {
 		struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
@@ -681,7 +606,7 @@
 
 		next = rb_next(&he_pair->rb_node_in);
 
-		cmp = block_pair_cmp(he_pair, he);
+		cmp = __block_info__cmp(he_pair, he);
 		if (!cmp)
 			return he_pair;
 	}
@@ -689,6 +614,21 @@
 	return NULL;
 }
 
+static void init_spark_values(unsigned long *svals, int num)
+{
+	for (int i = 0; i < num; i++)
+		svals[i] = 0;
+}
+
+static void update_spark_value(unsigned long *svals, int num,
+			       struct stats *stats, u64 val)
+{
+	int n = stats->n;
+
+	if (n < num)
+		svals[n] = val;
+}
+
 static void compute_cycles_diff(struct hist_entry *he,
 				struct hist_entry *pair)
 {
@@ -697,6 +637,26 @@
 		pair->diff.cycles =
 			pair->block_info->cycles_aggr / pair->block_info->num_aggr -
 			he->block_info->cycles_aggr / he->block_info->num_aggr;
+
+		if (!cycles_hist)
+			return;
+
+		init_stats(&pair->diff.stats);
+		init_spark_values(pair->diff.svals, NUM_SPARKS);
+
+		for (int i = 0; i < pair->block_info->num; i++) {
+			u64 val;
+
+			if (i >= he->block_info->num || i >= NUM_SPARKS)
+				break;
+
+			val = llabs(pair->block_info->cycles_spark[i] -
+				     he->block_info->cycles_spark[i]);
+
+			update_spark_value(pair->diff.svals, NUM_SPARKS,
+					   &pair->diff.stats, val);
+			update_stats(&pair->diff.stats, val);
+		}
 	}
 }
 
@@ -720,13 +680,6 @@
 	}
 }
 
-static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
-{
-	/* Skip the calculation of column length in output_resort */
-	he->filtered = true;
-	return 0;
-}
-
 static void hists__precompute(struct hists *hists)
 {
 	struct rb_root_cached *root;
@@ -747,8 +700,11 @@
 		he   = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&he->rb_node_in);
 
-		if (compute == COMPUTE_CYCLES)
-			process_block_per_sym(he);
+		if (compute == COMPUTE_CYCLES) {
+			bh = container_of(he, struct block_hist, he);
+			init_block_hist(bh);
+			block_info__process_sym(he, bh, NULL, 0);
+		}
 
 		data__for_each_file_new(i, d) {
 			pair = get_pair_data(he, d);
@@ -767,16 +723,18 @@
 				compute_wdiff(he, pair);
 				break;
 			case COMPUTE_CYCLES:
-				process_block_per_sym(pair);
-				bh = container_of(he, struct block_hist, he);
 				pair_bh = container_of(pair, struct block_hist,
 						       he);
+				init_block_hist(pair_bh);
+				block_info__process_sym(pair, pair_bh, NULL, 0);
+
+				bh = container_of(he, struct block_hist, he);
 
 				if (bh->valid && pair_bh->valid) {
 					block_hists_match(&bh->block_hists,
 							  &pair_bh->block_hists);
-					hists__output_resort_cb(&pair_bh->block_hists,
-								NULL, filter_cb);
+					hists__output_resort(&pair_bh->block_hists,
+							     NULL);
 				}
 				break;
 			default:
@@ -1043,7 +1001,7 @@
 
 		if (!quiet) {
 			fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
-				perf_evsel__name(evsel_base));
+				evsel__name(evsel_base));
 		}
 
 		first = false;
@@ -1052,16 +1010,61 @@
 			data__fprintf();
 
 		/* Don't sort callchain for perf diff */
-		perf_evsel__reset_sample_bit(evsel_base, CALLCHAIN);
+		evsel__reset_sample_bit(evsel_base, CALLCHAIN);
 
 		hists__process(hists_base);
 	}
 }
 
+static int process_base_stream(struct data__file *data_base,
+			       struct data__file *data_pair,
+			       const char *title __maybe_unused)
+{
+	struct evlist *evlist_base = data_base->session->evlist;
+	struct evlist *evlist_pair = data_pair->session->evlist;
+	struct evsel *evsel_base, *evsel_pair;
+	struct evsel_streams *es_base, *es_pair;
+
+	evlist__for_each_entry(evlist_base, evsel_base) {
+		evsel_pair = evsel_match(evsel_base, evlist_pair);
+		if (!evsel_pair)
+			continue;
+
+		es_base = evsel_streams__entry(data_base->evlist_streams,
+					       evsel_base->idx);
+		if (!es_base)
+			return -1;
+
+		es_pair = evsel_streams__entry(data_pair->evlist_streams,
+					       evsel_pair->idx);
+		if (!es_pair)
+			return -1;
+
+		evsel_streams__match(es_base, es_pair);
+		evsel_streams__report(es_base, es_pair);
+	}
+
+	return 0;
+}
+
+static void stream_process(void)
+{
+	/*
+	 * Stream comparison only supports two data files.
+	 * perf.data.old and perf.data. data__files[0] is perf.data.old,
+	 * data__files[1] is perf.data.
+	 */
+	process_base_stream(&data__files[0], &data__files[1],
+			    "# Output based on old perf data:\n#\n");
+}
+
 static void data__free(struct data__file *d)
 {
 	int col;
 
+	if (d->evlist_streams)
+		evlist_streams__delete(d->evlist_streams);
+
 	for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
 		struct diff_hpp_fmt *fmt = &d->fmt[col];
 
@@ -1215,9 +1218,21 @@
 
 		if (pdiff.ptime_range)
 			zfree(&pdiff.ptime_range);
+
+		if (compute == COMPUTE_STREAM) {
+			d->evlist_streams = evlist__create_streams(
+						d->session->evlist, 5);
+			if (!d->evlist_streams) {
+				ret = -ENOMEM;
+				goto out_delete;
+			}
+		}
 	}
 
-	data_process();
+	if (compute == COMPUTE_STREAM)
+		stream_process();
+	else
+		data_process();
 
  out_delete:
 	data__for_each_file(i, d) {
@@ -1255,6 +1270,9 @@
 		    "Show period values."),
 	OPT_BOOLEAN('F', "formula", &show_formula,
 		    "Show formula."),
+	OPT_BOOLEAN(0, "cycles-hist", &cycles_hist,
+		    "Show cycles histogram and standard deviation "
+		    "- WARNING: use only with -c cycles."),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -1287,6 +1305,8 @@
 		   "only consider symbols in these pids"),
 	OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "only consider symbols in these tids"),
+	OPT_BOOLEAN(0, "stream", &pdiff.stream,
+		    "Enable hot streams comparison."),
 	OPT_END()
 };
 
@@ -1355,7 +1375,8 @@
 	end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
 				he->ms.sym);
 
-	if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+	if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
+	    (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
 		scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
 			  start_line, end_line, block_he->diff.cycles);
 	} else {
@@ -1462,6 +1483,90 @@
 	return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
 }
 
+static int all_zero(unsigned long *vals, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		if (vals[i] != 0)
+			return 0;
+	return 1;
+}
+
+static int print_cycles_spark(char *bf, int size, unsigned long *svals, u64 n)
+{
+	int printed;
+
+	if (n <= 1)
+		return 0;
+
+	if (n > NUM_SPARKS)
+		n = NUM_SPARKS;
+	if (all_zero(svals, n))
+		return 0;
+
+	printed = print_spark(bf, size, svals, n);
+	printed += scnprintf(bf + printed, size - printed, " ");
+	return printed;
+}
+
+static int hpp__color_cycles_hist(struct perf_hpp_fmt *fmt,
+			    struct perf_hpp *hpp, struct hist_entry *he)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+	struct hist_entry *pair = get_pair_fmt(he, dfmt);
+	struct block_hist *bh = container_of(he, struct block_hist, he);
+	struct block_hist *bh_pair;
+	struct hist_entry *block_he;
+	char spark[32], buf[128];
+	double r;
+	int ret, pad;
+
+	if (!pair) {
+		if (bh->block_idx)
+			hpp->skip = true;
+
+		goto no_print;
+	}
+
+	bh_pair = container_of(pair, struct block_hist, he);
+
+	block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
+	if (!block_he) {
+		hpp->skip = true;
+		goto no_print;
+	}
+
+	ret = print_cycles_spark(spark, sizeof(spark), block_he->diff.svals,
+				 block_he->diff.stats.n);
+
+	r = rel_stddev_stats(stddev_stats(&block_he->diff.stats),
+			     avg_stats(&block_he->diff.stats));
+
+	if (ret) {
+		/*
+		 * Padding spaces if number of sparks less than NUM_SPARKS
+		 * otherwise the output is not aligned.
+		 */
+		pad = NUM_SPARKS - ((ret - 1) / 3);
+		scnprintf(buf, sizeof(buf), "%s%5.1f%% %s", "\u00B1", r, spark);
+		ret = scnprintf(hpp->buf, hpp->size, "%*s",
+				dfmt->header_width, buf);
+
+		if (pad) {
+			ret += scnprintf(hpp->buf + ret, hpp->size - ret,
+					 "%-*s", pad, " ");
+		}
+
+		return ret;
+	}
+
+no_print:
+	return scnprintf(hpp->buf, hpp->size, "%*s",
+			dfmt->header_width, " ");
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -1536,7 +1641,7 @@
 
 	default:
 		BUG_ON(1);
-	};
+	}
 }
 
 static void
@@ -1667,6 +1772,10 @@
 		fmt->color = hpp__color_cycles;
 		fmt->sort  = hist_entry__cmp_nop;
 		break;
+	case PERF_HPP_DIFF__CYCLES_HIST:
+		fmt->color = hpp__color_cycles_hist;
+		fmt->sort  = hist_entry__cmp_nop;
+		break;
 	default:
 		fmt->sort  = hist_entry__cmp_nop;
 		break;
@@ -1692,10 +1801,14 @@
 		 *   PERF_HPP_DIFF__DELTA
 		 *   PERF_HPP_DIFF__RATIO
 		 *   PERF_HPP_DIFF__WEIGHTED_DIFF
+		 *   PERF_HPP_DIFF__CYCLES
 		 */
 		data__hpp_register(d, i ? compute_2_hpp[compute] :
 					  PERF_HPP_DIFF__BASELINE);
 
+		if (cycles_hist && i)
+			data__hpp_register(d, PERF_HPP_DIFF__CYCLES_HIST);
+
 		/*
 		 * And the rest:
 		 *
@@ -1850,6 +1963,12 @@
 	if (quiet)
 		perf_quiet_option();
 
+	if (cycles_hist && (compute != COMPUTE_CYCLES))
+		usage_with_options(diff_usage, options);
+
+	if (pdiff.stream)
+		compute = COMPUTE_STREAM;
+
 	symbol__annotation_init();
 
 	if (symbol__init(NULL) < 0)
@@ -1861,13 +1980,26 @@
 	if (check_file_brstack() < 0)
 		return -1;
 
-	if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack)
+	if ((compute == COMPUTE_CYCLES || compute == COMPUTE_STREAM)
+	    && !pdiff.has_br_stack) {
 		return -1;
+	}
 
-	if (ui_init() < 0)
-		return -1;
+	if (compute == COMPUTE_STREAM) {
+		symbol_conf.show_branchflag_count = true;
+		symbol_conf.disable_add2line_warn = true;
+		callchain_param.mode = CHAIN_FLAT;
+		callchain_param.key = CCKEY_SRCLINE;
+		callchain_param.branch_callstack = 1;
+		symbol_conf.use_callchain = true;
+		callchain_register_param(&callchain_param);
+		sort_order = "srcline,symbol,dso";
+	} else {
+		if (ui_init() < 0)
+			return -1;
 
-	sort__mode = SORT_MODE__DIFF;
+		sort__mode = SORT_MODE__DIFF;
+	}
 
 	if (setup_sorting(NULL) < 0)
 		usage_with_options(diff_usage, options);