Firestorm: TST (immediate, 32-bit) measurements

Code:

  tst w0, #3

Initialization

  mov x0, 1

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	1e	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst int alu (97)	l1d cache writeback (a8)	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	f5	f6	f7	f8	fd
1004	369	3	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	3	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	2	0	36	25	1000	1000	1000	5000	1	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	3	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	2	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	2	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	6	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	2	0	36	25	1000	1000	1000	5000	1	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	2	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	3	0	36	25	1000	1000	1000	5000	0	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370
1004	369	3	0	36	25	1000	1000	1000	5000	1	369	369	206	3	225	1000	1000	1000	369	66	1	1	1001	1000	0	0	73	2	18	2	2	366	1000	370	370	370	370	370

Test 2: Latency 2->1

Chain cycles: 1

Code:

  tst w0, #3
  cset x0, cc

Initialization

  mov x0, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	09	18	19	1e	1f	3a	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	61	69	6a	6d	6e	map stall dispatch (70)	flags prf full (73)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d0	d2	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20204	20035	150	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20200	20200	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	1	1	16	2	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	1	1	16	1	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	0	1	16	4	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	1	0	0	0	0	0	232	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	1	1	16	1	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1337	5	0	1	16	1	1	20040	20000	10100	20036	20036	20036	20036	20127
20204	20035	150	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	0	1	16	1	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	21	0	0	103	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	0	1	16	1	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	7	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	0	1	48	1	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	149	0	0	0	0	0	0	61	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	1	1	16	1	1	20011	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	451	19930	25	20100	20100	20112	1297233	0	0	49	16955	20035	20035	17425	0	6	17487	20112	20224	20224	20035	104	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1318	5	1	1	16	1	1	20011	20000	10100	20036	20036	20036	20036	20036

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk data (08)	19	1e	1f	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	a9	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20024	20035	150	0	0	0	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1270	1	27	1	2	19995	20000	10010	20036	20036	20036	20036	20082
20024	20035	150	0	0	0	0	124	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1286	1	27	1	1	19995	20022	10010	20172	20036	20036	20036	20082
20024	20035	150	1	0	0	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	3	1270	1	27	1	1	19995	20000	10010	20036	20036	20215	20036	20036
20024	20035	150	0	0	0	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	0	0	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20081	20127	20036
20024	20035	150	0	0	12	0	168	19918	46	20010	20010	20092	1297874	0	49	16955	20035	20035	17444	7	17530	20010	20020	20117	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	0	0	0	103	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	1	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	0	0	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1270	2	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	0	0	0	360	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	1	0	3	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	0	0	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	20020	20035	104	1	1	20021	10	9	10	20010	10010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036

Test 3: throughput

Count: 8

Code:

  tst w0, #3
  tst w0, #3
  tst w0, #3
  tst w0, #3
  tst w0, #3
  tst w0, #3
  tst w0, #3
  tst w0, #3

Initialization

  mov x0, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3342

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	1e	3a	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d tlb access (a0)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80204	26761	200	1	0	0	1	3	2	266	27	80115	80115	80121	400590	0	49	23659	26739	26739	16679	16	16689	80258	80367	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	8	8	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	276	2	34	27	80115	80115	80121	400590	1	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	8	9	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	213	2	34	27	80115	80115	80121	400590	1	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	3	8	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	336	2	34	27	80115	80115	80121	400590	0	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	8	8	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	240	2	34	27	80115	80115	80121	400590	1	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	10	16	3	8	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	0	2	338	27	80115	80115	80121	400590	1	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	9	9	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	216	2	34	27	80115	80115	80121	400590	0	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	4	0	3	0	1	1	1	5122	8	16	10	8	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	228	2	34	27	80115	80115	80121	400590	0	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	132	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	8	8	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	210	2	34	27	80115	80115	80121	400590	0	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	9	9	26736	80015	100	26740	26740	26740	26740	26740
80204	26739	200	1	0	0	1	24	2	34	27	80115	80115	80121	400590	0	49	23659	26739	26739	16679	6	16689	80121	80232	80232	26739	66	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	1	1	5122	8	16	8	8	26736	80015	100	26740	26740	26740	26740	26740

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3338

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d cache writeback (a8)	ac	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	eb	ec	? int retires (ef)	f5	f6	f7	f8	fd
80024	26722	200	311	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	2	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	35	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	528	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	16	10	26706	26706	26706	26706	26706
80024	26705	200	35	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	144	25	80010	80010	80010	400050	49	23625	26705	26710	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	35	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	199	35	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	35	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	0	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	35	25	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	1	0	5020	0	1	18	1	1	26701	80064	0	0	10	26706	26706	26706	26706	26706
80024	26705	200	35	47	80010	80010	80010	400050	49	23625	26705	26705	16665	3	16683	80010	80020	80020	26705	66	1	1	80021	10	9	10	80010	10	1	0	5020	0	1	18	1	1	26701	80000	0	0	10	26706	26706	26706	26706	26706

TST (immediate, 32-bit)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 2->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations