Icestorm: FMLS (vector, 4H) measurements

Code:

  fmls v0.4h, v1.4h, v2.4h

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	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	3000	1	1000

Test 2: Latency 1->1

Code:

  fmls v0.4h, v1.4h, v2.4h

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): 4.0033

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	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30132	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0033

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	40033	10021	21	10000	20	10000	70	1028890	10050	20	10041	20	30012	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	66	1028904	10050	20	10044	20	30012	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10

Test 3: Latency 1->2

Code:

  fmls 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): 4.0033

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	40033	10101	101	10000	100	10000	300	1028557	10100	200	10006	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	202	0	30138	2	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	114	385257	3819	76	3796	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	0	30012	1	0	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0033

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	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30132	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10

Test 4: Latency 1->3

Code:

  fmls 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): 4.0033

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	40033	10101	101	10000	100	10000	300	1028557	10100	200	10006	200	30018	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30132	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0033

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	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10025	40066	10025	21	10004	20	10030	70	1028557	10020	20	10000	20	30000	11	10000	10
10025	40066	10025	21	10004	20	10030	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028904	10050	20	10046	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30129	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	30000	11	10000	10

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.4h, v8.4h, v9.4h
  movi v1.16b, 0
  fmls v1.4h, v8.4h, v9.4h
  movi v2.16b, 0
  fmls v2.4h, v8.4h, v9.4h
  movi v3.16b, 0
  fmls v3.4h, v8.4h, v9.4h
  movi v4.16b, 0
  fmls v4.4h, v8.4h, v9.4h
  movi v5.16b, 0
  fmls v5.4h, v8.4h, v9.4h
  movi v6.16b, 0
  fmls v6.4h, v8.4h, v9.4h
  movi v7.16b, 0
  fmls 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): 0.5011

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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
160204	40491	80110	101	80009	100	80013	300	320056	80113	200	80013	200	0	240039	1	0	160000	100
160204	40110	80110	101	80009	100	80013	300	320052	80112	200	80012	200	0	240039	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240144	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100
160204	40096	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	0	240036	1	0	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5055

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	43763	80020	11	80009	10	80013	30	320000	80010	20	80000	20	0	240150	1	0	160000	10
160024	41351	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40392	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40406	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40442	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40442	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40528	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40415	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10
160024	40408	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240147	1	0	160000	10
160024	40549	80011	11	80000	10	80000	30	320000	80010	20	80000	20	0	240000	1	0	160000	10

Test 6: throughput

Count: 16

Code:

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

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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
160204	80082	160105	101	160004	100	160008	0	300	0	640044	160110	200	0	160014	200	0	480042	1	0	160000	100
160204	80036	160107	101	160006	100	160010	0	300	0	640036	160108	200	0	160012	200	0	480042	1	0	160000	100
160204	80036	160107	101	160006	100	160010	0	300	0	640224	160158	200	0	160066	200	0	480039	1	0	160000	100
160204	80036	160105	101	160004	100	160008	0	300	0	640044	160110	200	0	160013	1112	755	480192	413	285	160001	502
160204	80036	160107	101	160006	100	160010	0	300	0	640044	160110	200	0	160013	200	0	480042	1	0	160000	100
160204	80036	160107	101	160006	100	160010	0	300	0	640044	160110	200	0	160013	200	0	480036	1	0	160000	100
160204	80036	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	0	480036	1	0	160000	100
160204	80036	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	0	480036	1	0	160000	100
160204	80036	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	0	480036	1	0	160000	100
160204	80036	160105	101	160004	100	160008	0	300	0	640036	160108	200	0	160012	200	0	480036	1	0	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5003

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	80199	160017	11	160006	10	160010	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80071	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160025	80086	160056	11	160045	10	160057	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10
160024	80043	160011	11	160000	10	160000	30	640000	160010	20	160000	20	480000	1	160000	10

FMLS (vector, 4H)

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