Icestorm: SQDMLAL (by element, D) measurements

Code:

  sqdmlal d0, s1, v2.s[1]

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:

  sqdmlal d0, s1, v2.s[1]

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)	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	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	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	10004	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

Test 3: Latency 1->2

Code:

  sqdmlal d0, s0, v1.s[1]

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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10006	200	0	30018	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	0	30012	1	0	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	67	769247	10051	20	10044	20	30000	11	10000	10
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	66	771089	10152	20	10161	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:

  sqdmlal d0, s1, v0.s[1]

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	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	68	769247	10051	20	10043	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	30015	11	10000	10

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal d0, s8, v9.s[1]
  movi v1.16b, 0
  sqdmlal d1, s8, v9.s[1]
  movi v2.16b, 0
  sqdmlal d2, s8, v9.s[1]
  movi v3.16b, 0
  sqdmlal d3, s8, v9.s[1]
  movi v4.16b, 0
  sqdmlal d4, s8, v9.s[1]
  movi v5.16b, 0
  sqdmlal d5, s8, v9.s[1]
  movi v6.16b, 0
  sqdmlal d6, s8, v9.s[1]
  movi v7.16b, 0
  sqdmlal d7, s8, v9.s[1]

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	40466	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	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
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): 0.5052

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)	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	43780	80020	11	80009	10	80013	0	30	0	320056	80023	20	0	80013	20	240000	1	160000	10
160024	41250	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40407	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40419	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40419	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40418	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40418	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40517	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40449	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10
160024	40448	80011	11	80000	10	80000	0	30	0	320000	80010	20	0	80000	20	240000	1	160000	10

Test 6: throughput

Count: 12

Code:

  sqdmlal d0, s12, v13.s[1]
  sqdmlal d1, s12, v13.s[1]
  sqdmlal d2, s12, v13.s[1]
  sqdmlal d3, s12, v13.s[1]
  sqdmlal d4, s12, v13.s[1]
  sqdmlal d5, s12, v13.s[1]
  sqdmlal d6, s12, v13.s[1]
  sqdmlal d7, s12, v13.s[1]
  sqdmlal d8, s12, v13.s[1]
  sqdmlal d9, s12, v13.s[1]
  sqdmlal d10, s12, v13.s[1]
  sqdmlal d11, s12, v13.s[1]

Initialization

  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
120204	60105	120105	101	120004	100	120008	300	480044	120110	200	120014	200	0	360039	1	0	120000	100
120204	60035	120107	101	120006	100	120010	300	480036	120108	200	120012	200	0	360036	1	0	120000	100
120205	60071	120145	101	120044	100	120056	300	480044	120110	200	120013	200	0	360036	1	0	120000	100
120204	60035	120105	101	120004	100	120008	300	480036	120108	200	120012	200	0	360036	1	0	120000	100
120204	60035	120105	101	120004	100	120008	300	480036	120108	200	120012	200	0	360036	1	0	120000	100
120204	60035	120107	101	120006	100	120010	300	480044	120110	200	120013	200	0	360036	1	0	120000	100
120204	60035	120105	101	120004	100	120008	300	480036	120108	200	120012	200	0	360036	1	0	120000	100
120204	60035	120105	101	120004	100	120008	300	480036	120108	200	120012	200	0	360036	1	0	120000	100
120204	60035	120105	101	120004	100	120008	300	480036	120108	200	120012	200	0	360036	1	0	120000	100
120204	60035	120105	101	120004	100	120008	300	480036	120108	200	120012	200	0	360036	1	0	120000	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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
120024	60252	120015	11	120004	10	120008	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10
120024	60035	120011	11	120000	10	120000	30	480000	120010	20	120000	20	0	360000	1	0	120000	10

SQDMLAL (by element, D)

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