Icestorm: BSL (vector, 16B) measurements

Code:

  bsl v0.16b, v1.16b, v2.16b

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(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	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000
1004	2033	1001	1	1000	1000	50248	1000	1000	3000	1	1000

Test 2: Latency 1->1

Code:

  bsl v0.16b, v1.16b, v2.16b

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(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	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10205	20066	10109	101	10008	100	10034	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10205	20066	10109	101	10008	102	10034	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	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)	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	509248	10020	20	0	10004	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	68	0	509580	10054	20	0	10048	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	658	24634	13728	509580	11730	1442	758	10048	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10
10025	20066	10029	21	10008	20	10034	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	0	70	0	509248	10020	20	0	10000	20	30000	11	10000	10

Test 3: Latency 1->2

Code:

  bsl v0.16b, v0.16b, v1.16b

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	30018	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10006	200	30018	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10006	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	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	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10

Test 4: Latency 1->3

Code:

  bsl v0.16b, v1.16b, v0.16b

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	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	1	10000	100
10204	20033	10101	101	10000	100	10000	300	509248	10100	200	10004	200	30012	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	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10
10024	20033	10021	21	10000	20	10000	70	509248	10020	20	10000	20	30000	11	10000	10

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  bsl v0.16b, v8.16b, v9.16b
  movi v1.16b, 0
  bsl v1.16b, v8.16b, v9.16b
  movi v2.16b, 0
  bsl v2.16b, v8.16b, v9.16b
  movi v3.16b, 0
  bsl v3.16b, v8.16b, v9.16b
  movi v4.16b, 0
  bsl v4.16b, v8.16b, v9.16b
  movi v5.16b, 0
  bsl v5.16b, v8.16b, v9.16b
  movi v6.16b, 0
  bsl v6.16b, v8.16b, v9.16b
  movi v7.16b, 0
  bsl v7.16b, v8.16b, v9.16b

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): 0.5011

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)	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	40538	80109	101	80008	100	80012	300	320056	80113	200	80013	200	240039	1	160000	100
160204	40110	80110	101	80009	100	80013	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240039	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5053

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	44176	80054	11	80043	10	80049	30	320056	80023	20	80013	20	240000	1	160000	10
160024	41238	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240102	1	160000	10
160024	40516	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40431	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40423	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40406	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40432	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40423	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40425	80011	11	80000	10	80000	30	320144	80046	20	80036	20	240000	1	160000	10
160024	44285	80020	11	80009	10	80013	30	320000	80010	20	80000	20	240000	1	160000	10

Test 6: throughput

Count: 16

Code:

  bsl v0.16b, v16.16b, v17.16b
  bsl v1.16b, v16.16b, v17.16b
  bsl v2.16b, v16.16b, v17.16b
  bsl v3.16b, v16.16b, v17.16b
  bsl v4.16b, v16.16b, v17.16b
  bsl v5.16b, v16.16b, v17.16b
  bsl v6.16b, v16.16b, v17.16b
  bsl v7.16b, v16.16b, v17.16b
  bsl v8.16b, v16.16b, v17.16b
  bsl v9.16b, v16.16b, v17.16b
  bsl v10.16b, v16.16b, v17.16b
  bsl v11.16b, v16.16b, v17.16b
  bsl v12.16b, v16.16b, v17.16b
  bsl v13.16b, v16.16b, v17.16b
  bsl v14.16b, v16.16b, v17.16b
  bsl v15.16b, v16.16b, v17.16b

Initialization

  movi v16.16b, 17
  movi v17.16b, 18

(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)	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	80057	160106	101	160005	100	160009	0	300	0	640044	160110	200	0	160014	200	480039	1	160000	100
160204	80044	160107	101	160006	100	160010	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640208	160154	200	0	160064	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80034	160105	101	160004	100	160008	0	300	0	640208	160154	200	0	160063	200	480039	1	160000	100
160204	80034	160105	101	160004	100	160008	196	17012	10623	640200	160646	622	250	160062	200	480039	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)	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)
160024	80333	160017	11	160006	10	160010	30	640044	160020	20	160014	20	480000	1	160000	10
160024	80051	160011	11	160000	10	160000	30	640208	160064	20	160060	20	480000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80034	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80034	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80034	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160025	80073	160052	11	160041	10	160053	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80034	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80034	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80060	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10

BSL (vector, 16B)

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: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 6: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations