Icestorm: SUBHN2 (vector, 4S) measurements

Code:

  subhn2 v0.8h, v1.4s, v2.4s

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	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	3000	1	1000

Test 2: Latency 1->1

Code:

  subhn2 v0.8h, v1.4s, v2.4s

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): 3.0033

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	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

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	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10

Test 3: Latency 1->2

Code:

  subhn2 v0.8h, v0.4s, v1.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0033

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	30033	10101	101	10000	100	10000	300	768905	10100	200	10006	200	30018	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30132	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

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)	schedule ldst uop (55)	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	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10004	20	30012	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	0	20	10000	70	768905	10020	20	10000	20	30132	11	10000	10

Test 4: Latency 1->3

Code:

  subhn2 v0.8h, v1.4s, v0.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0033

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	30033	10101	101	10000	100	10000	300	768905	10100	200	10006	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10006	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0033

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	30033	10021	21	10000	20	10000	70	768905	10020	20	10004	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	30000	11	10000	10

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  subhn2 v0.8h, v8.4s, v9.4s
  movi v1.16b, 0
  subhn2 v1.8h, v8.4s, v9.4s
  movi v2.16b, 0
  subhn2 v2.8h, v8.4s, v9.4s
  movi v3.16b, 0
  subhn2 v3.8h, v8.4s, v9.4s
  movi v4.16b, 0
  subhn2 v4.8h, v8.4s, v9.4s
  movi v5.16b, 0
  subhn2 v5.8h, v8.4s, v9.4s
  movi v6.16b, 0
  subhn2 v6.8h, v8.4s, v9.4s
  movi v7.16b, 0
  subhn2 v7.8h, v8.4s, v9.4s

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	40464	80110	101	80009	100	80013	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	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320204	80150	200	80050	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	320056	80113	200	80013	200	240036	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240363	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	43966	80056	11	80045	10	80049	30	320056	80023	20	80013	20	240000	1	160000	10
160024	41337	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40424	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40428	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	40417	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40417	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40395	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40417	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40417	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10

Test 6: throughput

Count: 16

Code:

  subhn2 v0.8h, v16.4s, v17.4s
  subhn2 v1.8h, v16.4s, v17.4s
  subhn2 v2.8h, v16.4s, v17.4s
  subhn2 v3.8h, v16.4s, v17.4s
  subhn2 v4.8h, v16.4s, v17.4s
  subhn2 v5.8h, v16.4s, v17.4s
  subhn2 v6.8h, v16.4s, v17.4s
  subhn2 v7.8h, v16.4s, v17.4s
  subhn2 v8.8h, v16.4s, v17.4s
  subhn2 v9.8h, v16.4s, v17.4s
  subhn2 v10.8h, v16.4s, v17.4s
  subhn2 v11.8h, v16.4s, v17.4s
  subhn2 v12.8h, v16.4s, v17.4s
  subhn2 v13.8h, v16.4s, v17.4s
  subhn2 v14.8h, v16.4s, v17.4s
  subhn2 v15.8h, v16.4s, v17.4s

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)	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)
160204	80059	160108	101	160007	100	160011	300	640044	160110	200	160014	200	0	480042	1	0	160000	100
160204	80035	160107	101	160006	100	160010	300	640044	160110	200	160013	200	0	480039	1	0	160000	100
160204	80035	160107	101	160006	100	160010	300	640036	160108	200	160012	200	0	480039	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	480036	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	480036	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	480036	1	0	160000	100
160205	80070	160143	101	160042	100	160054	300	640036	160108	200	160012	200	0	480036	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	480036	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	480036	1	0	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	0	480036	1	0	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)	schedule ldst uop (55)	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	80261	160017	11	160006	0	10	160010	30	640044	160020	20	160014	20	480000	1	160000	10
160024	80102	160011	11	160000	0	10	160000	30	640216	160066	20	160063	20	480000	1	160000	10
160024	80035	160011	11	160000	0	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80035	160011	11	160000	0	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80035	160011	11	160000	0	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80035	160011	11	160000	0	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80035	160011	11	160000	0	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
168703	110173	167150	4551	160043	2556	4206	160055	30	640044	160020	20	160013	20	480042	1	160000	10
160024	80381	160017	11	160006	0	10	160010	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80035	160011	11	160000	0	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10

SUBHN2 (vector, 4S)

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