Icestorm: FMINNM (vector, 4H) measurements

Code:

  fminnm v0.4h, v0.4h, v1.4h

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.001

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	2000	1	1000

Test 2: Latency 1->2

Code:

  fminnm v0.4h, v0.4h, v1.4h

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0033

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10006	200	20012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20088	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	20008	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0033

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
10024	20033	10021	21	10000	20	10000	70	509247	10020	20	10006	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	20000	11	10000	10

Test 3: Latency 1->3

Code:

  fminnm v0.4h, v1.4h, v0.4h

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0033

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10006	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	0	20008	1	0	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0033

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
10024	20033	10021	21	10000	20	10000	0	70	0	509247	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	69	0	509247	10020	20	0	10004	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	20000	11	10000	10

Test 4: throughput

Count: 8

Code:

  fminnm v0.4h, v8.4h, v9.4h
  fminnm v1.4h, v8.4h, v9.4h
  fminnm v2.4h, v8.4h, v9.4h
  fminnm v3.4h, v8.4h, v9.4h
  fminnm v4.4h, v8.4h, v9.4h
  fminnm v5.4h, v8.4h, v9.4h
  fminnm v6.4h, v8.4h, v9.4h
  fminnm v7.4h, v8.4h, v9.4h

Initialization

  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5004

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	dispatch ldst uop (58)	int uops in schedulers (59)	simd uops in schedulers (5a)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map ldst uop (7d)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
80204	40057	80105	101	80004	100	80008	0	300	0	320044	80110	200	0	80014	202	160118	1	80000	100
80204	40044	80107	101	80006	100	80010	0	300	0	320224	80155	200	0	80059	200	160310	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320240	80159	200	0	80063	200	160024	1	80000	100
80204	40275	80249	101	80148	100	80152	0	300	0	320232	80157	200	0	80061	200	160118	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320036	80108	200	0	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320036	80108	200	0	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320036	80108	200	0	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320036	80108	200	0	80012	200	160120	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320036	80108	200	0	80012	200	160024	1	80000	100
80204	40034	80105	101	80004	100	80008	0	300	0	320036	80108	200	0	80012	200	160024	1	80000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5004

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
80024	40117	80027	21	80006	20	80010	68	320052	80032	20	80018	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	69	320044	80030	20	80016	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40034	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10

FMINNM (vector, 4H)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations