Icestorm: FMLS (by element, H) measurements

Code:

  fmls h0, h1, v2.h[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	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 h0, h1, v2.h[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): 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	30132	1	10000	100
10204	40033	10101	101	10000	100	10000	307	1028904	10132	202	10046	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

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	10004	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	22	30138	12	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 h0, h0, v1.h[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): 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	30012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	202	30126	2	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	10006	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
10025	40066	10027	23	10004	22	10030	70	1028557	10020	20	10000	20	30000	11	10000	10
10024	40235	10045	21	10024	20	10124	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 h0, h1, v0.h[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): 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)	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	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10006	200	30018	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	100	10000	300	1028557	10100	200	10004	200	30012	1	10000	100
10205	40066	10107	103	10004	0	102	10030	300	1028557	10100	200	10004	200	30012	1	10000	100
10204	40033	10101	101	10000	0	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
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	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	30018	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 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls h0, h8, v9.h[1]
  movi v1.16b, 0
  fmls h1, h8, v9.h[1]
  movi v2.16b, 0
  fmls h2, h8, v9.h[1]
  movi v3.16b, 0
  fmls h3, h8, v9.h[1]
  movi v4.16b, 0
  fmls h4, h8, v9.h[1]
  movi v5.16b, 0
  fmls h5, h8, v9.h[1]
  movi v6.16b, 0
  fmls h6, h8, v9.h[1]
  movi v7.16b, 0
  fmls h7, h8, v9.h[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	40634	80109	101	80008	100	80012	300	320056	80113	200	80013	200	240039	1	160000	100
160204	40116	80109	101	80008	100	80012	300	320052	80112	200	80012	200	240039	1	160000	100
160204	40098	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	240144	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)
160024	43881	80020	11	80009	10	80013	30	320000	80010	20	80000	20	240000	1	160000	10
160024	41364	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	40420	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40425	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40420	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40420	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	40422	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10
160024	40401	80011	11	80000	10	80000	30	320000	80010	20	80000	20	240000	1	160000	10

Test 6: throughput

Count: 12

Code:

  fmls h0, h12, v13.h[1]
  fmls h1, h12, v13.h[1]
  fmls h2, h12, v13.h[1]
  fmls h3, h12, v13.h[1]
  fmls h4, h12, v13.h[1]
  fmls h5, h12, v13.h[1]
  fmls h6, h12, v13.h[1]
  fmls h7, h12, v13.h[1]
  fmls h8, h12, v13.h[1]
  fmls h9, h12, v13.h[1]
  fmls h10, h12, v13.h[1]
  fmls h11, h12, v13.h[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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
120204	60085	120107	101	120006	100	120010	300	480044	120110	200	120014	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480216	120156	200	120064	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	120000	100
120204	60036	120105	101	120004	100	120008	300	480036	120108	200	120012	200	360036	1	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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
120024	60098	120018	11	120007	10	120011	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360195	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10
120024	60036	120011	11	120000	10	120000	30	480000	120010	20	120000	20	360000	1	120000	10

FMLS (by element, H)

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