Icestorm: BIC (vector, immediate, 8H) measurements

Code:

  bic v0.8h, #1

Initialization

  movi v0.16b, 1

(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	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	1000	1	1000

Test 2: Latency 1->1

Code:

  bic v0.8h, #1

Initialization

  movi v0.16b, 1

(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)
10205	20066	10109	101	10008	100	10034	300	509248	10100	200	10004	200	10006	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	202	10046	2	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	1	10000	100
10205	20066	10111	103	10008	102	10034	300	509248	10100	200	10004	200	10004	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	10004	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	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10006	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	10000	11	10000	10

Test 3: throughput

Count: 8

Code:

  movi v0.16b, 0
  bic v0.8h, #1
  movi v1.16b, 0
  bic v1.8h, #1
  movi v2.16b, 0
  bic v2.8h, #1
  movi v3.16b, 0
  bic v3.8h, #1
  movi v4.16b, 0
  bic v4.8h, #1
  movi v5.16b, 0
  bic v5.8h, #1
  movi v6.16b, 0
  bic v6.8h, #1
  movi v7.16b, 0
  bic v7.8h, #1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5011

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)
160204	40469	80109	101	80008	100	80012	0	300	0	320056	80113	200	0	80013	200	80013	1	160000	100
160204	40110	80110	101	80009	100	80013	0	300	0	320056	80113	200	0	80013	200	80012	1	160000	100
160204	40086	80109	101	80008	100	80012	0	300	0	320052	80112	200	0	80012	200	80012	1	160000	100
160204	40086	80109	101	80008	100	80012	0	300	0	320052	80112	200	0	80012	200	80012	1	160000	100
160204	40086	80109	101	80008	100	80012	0	300	0	320052	80112	200	0	80012	200	80012	1	160000	100
160204	40086	80109	101	80008	100	80012	2557	41055	21997	320462	85822	4652	3076	80071	200	80013	1	160000	100
160204	40086	80109	101	80008	100	80012	0	300	0	320056	80113	200	0	80013	200	80013	1	160000	100
160204	40105	80110	101	80009	100	80013	0	300	0	320052	80112	200	0	80012	200	80012	1	160000	100
160204	40086	80109	101	80008	100	80012	0	300	0	320052	80112	200	0	80012	200	80012	1	160000	100
160204	40086	80109	101	80008	100	80012	0	300	0	320052	80112	200	0	80012	200	80012	1	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5052

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)
160025	43887	80054	11	80043	10	80049	30	320056	80023	20	80013	20	80000	1	160000	10
160024	41258	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40423	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40363	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40413	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160025	40470	80054	11	80043	10	80047	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40413	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40420	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40408	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10
160024	40420	80011	11	80000	10	80000	30	320000	80010	20	80000	20	80000	1	160000	10

Test 4: throughput

Count: 16

Code:

  bic v0.8h, #1
  bic v1.8h, #1
  bic v2.8h, #1
  bic v3.8h, #1
  bic v4.8h, #1
  bic v5.8h, #1
  bic v6.8h, #1
  bic v7.8h, #1
  bic v8.8h, #1
  bic v9.8h, #1
  bic v10.8h, #1
  bic v11.8h, #1
  bic v12.8h, #1
  bic v13.8h, #1
  bic v14.8h, #1
  bic v15.8h, #1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5002

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)
160204	80081	160105	101	160004	100	160008	300	640044	160110	200	160014	200	160014	1	160000	100
160204	80034	160107	101	160006	100	160010	300	640044	160110	200	160014	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640036	160108	200	160012	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640036	160108	200	160012	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640052	160112	200	160015	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640036	160108	200	160012	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640036	160108	200	160012	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640036	160108	200	160012	200	160012	1	160000	100
160204	80034	160105	101	160004	100	160008	300	640036	160108	200	160012	200	160012	1	160000	100
160204	80035	160109	101	160008	100	160012	300	640036	160108	200	160012	200	160060	1	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5002

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)
160024	80140	160017	11	160006	10	160010	0	30	0	640044	160020	20	0	160014	20	160000	1	160000	10
160024	80039	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160024	80034	160011	11	160000	10	160000	0	30	0	640200	160062	20	0	160060	20	160000	1	160000	10
160024	80034	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160024	80034	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160024	80034	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160025	80079	160050	11	160039	10	160051	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160024	80034	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160024	80044	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10
160024	80034	160011	11	160000	10	160000	0	30	0	640000	160010	20	0	160000	20	160000	1	160000	10

BIC (vector, immediate, 8H)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations