Icestorm: SUBHN2 (vector, 8H) measurements

Code:

  subhn2 v0.16b, v1.8h, v2.8h

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 v0.16b, v1.8h, v2.8h

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)	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)
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	769247	10131	200	10042	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	204	30600	2	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	307	769366	10135	202	10042	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30033	10101	101	10000	0	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30084	10111	103	10008	0	102	10033	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	10006	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 v0.16b, v0.8h, v1.8h

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	307	770543	10201	202	10124	206	30969	3	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30129	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30238	10135	103	10032	102	10132	300	768905	10100	200	10004	200	30018	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10006	200	30141	1	10000	100
10204	30033	10101	101	10000	100	10000	300	771074	10232	202	10163	200	30135	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	30012	1	10000	100
10204	30188	10127	103	10024	102	10099	376	779194	10749	224	10760	216	31929	8	10000	100
10204	30957	10255	111	10144	110	10594	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	769247	10051	20	10044	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 4: Latency 1->3

Code:

  subhn2 v0.16b, v1.8h, v0.8h

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	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	769247	10051	20	10044	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
10025	30066	10027	21	10006	20	10031	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 v0.16b, v8.8h, v9.8h
  movi v1.16b, 0
  subhn2 v1.16b, v8.8h, v9.8h
  movi v2.16b, 0
  subhn2 v2.16b, v8.8h, v9.8h
  movi v3.16b, 0
  subhn2 v3.16b, v8.8h, v9.8h
  movi v4.16b, 0
  subhn2 v4.16b, v8.8h, v9.8h
  movi v5.16b, 0
  subhn2 v5.16b, v8.8h, v9.8h
  movi v6.16b, 0
  subhn2 v6.16b, v8.8h, v9.8h
  movi v7.16b, 0
  subhn2 v7.16b, v8.8h, v9.8h

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)	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)
160204	40486	80109	101	80008	0	100	80012	300	320056	80113	200	80013	200	240036	1	160000	100
160204	40108	80110	101	80009	0	100	80013	300	320052	80112	200	80012	200	240150	1	160000	100
160204	40086	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240138	1	160000	100
160204	40086	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40096	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	0	100	80012	300	320052	80112	200	80012	200	240036	1	160000	100
160204	40086	80109	101	80008	0	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): 0.5052

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)
160024	43983	80020	11	80009	10	80013	30	320056	80023	20	80013	20	240039	1	160000	10
160024	41315	80020	11	80009	10	80013	30	320052	80022	20	80012	20	240000	1	160000	10
160024	40356	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40388	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40422	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40407	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40408	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	40428	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40408	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10

Test 6: throughput

Count: 16

Code:

  subhn2 v0.16b, v16.8h, v17.8h
  subhn2 v1.16b, v16.8h, v17.8h
  subhn2 v2.16b, v16.8h, v17.8h
  subhn2 v3.16b, v16.8h, v17.8h
  subhn2 v4.16b, v16.8h, v17.8h
  subhn2 v5.16b, v16.8h, v17.8h
  subhn2 v6.16b, v16.8h, v17.8h
  subhn2 v7.16b, v16.8h, v17.8h
  subhn2 v8.16b, v16.8h, v17.8h
  subhn2 v9.16b, v16.8h, v17.8h
  subhn2 v10.16b, v16.8h, v17.8h
  subhn2 v11.16b, v16.8h, v17.8h
  subhn2 v12.16b, v16.8h, v17.8h
  subhn2 v13.16b, v16.8h, v17.8h
  subhn2 v14.16b, v16.8h, v17.8h
  subhn2 v15.16b, v16.8h, v17.8h

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	80098	160106	101	160005	100	160009	0	300	0	640044	160110	200	0	160014	200	480039	1	160000	100
160204	80035	160107	101	160006	100	160010	0	300	0	640044	160110	200	0	160014	200	480042	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640044	160110	200	0	160014	200	480036	1	160000	100
160205	80070	160145	101	160044	100	160056	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	1	160000	100
160204	80035	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	480036	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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
160024	80137	160017	11	160006	10	160010	30	640044	160020	20	160014	20	0	480042	1	0	160000	10
160024	80052	160018	11	160007	10	160011	30	640044	160020	20	160013	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480195	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	0	480000	1	0	160000	10

SUBHN2 (vector, 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: 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