Icestorm: SUQADD (scalar, D) measurements

Code:

  suqadd d0, d1

Initialization

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

(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	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000
1004	3033	1001	1	1000	1000	75905	1000	1000	2000	1	1000

Test 2: Latency 1->1

Code:

  suqadd d0, d1

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	20012	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0084

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	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	67	768356	10053	20	10040	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20096	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20076	11	10000	10

Test 3: Latency 1->2

Code:

  suqadd d0, d0

Initialization

  movi v0.16b, 1

(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	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	768905	10100	200	10004	200	20008	1	10000	100
10204	30033	10101	101	10000	100	10000	300	769247	10131	202	10046	200	20008	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	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20088	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10
10024	30033	10021	21	10000	20	10000	70	768905	10020	20	10000	20	20000	11	10000	10

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  suqadd d0, d8
  movi v1.16b, 0
  suqadd d1, d8
  movi v2.16b, 0
  suqadd d2, d8
  movi v3.16b, 0
  suqadd d3, d8
  movi v4.16b, 0
  suqadd d4, d8
  movi v5.16b, 0
  suqadd d5, d8
  movi v6.16b, 0
  suqadd d6, d8
  movi v7.16b, 0
  suqadd d7, d8

Initialization

  movi v8.16b, 9

(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	40506	80109	101	80008	100	80012	300	320056	80113	200	80013	200	160024	1	160000	100
160204	40108	80110	101	80009	100	80013	300	320052	80112	200	80012	200	160026	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40107	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100
160204	40086	80109	101	80008	100	80012	300	320052	80112	200	80012	200	160024	1	160000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5057

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	43863	80019	11	80008	10	80012	30	320052	80022	20	80012	20	160000	1	160000	10
160024	41331	80011	11	80000	10	80000	30	320568	80152	20	80142	20	160000	1	160000	10
160024	40532	80011	11	80000	10	80000	30	320148	80047	20	80037	20	160168	1	160000	10
160024	40578	80011	11	80000	10	80000	30	320000	80010	20	80000	20	160072	1	160000	10
160024	40407	80011	11	80000	10	80000	30	320000	80010	20	80000	20	160000	1	160000	10
160024	40543	80047	11	80036	10	80036	30	320000	80010	20	80000	20	160000	1	160000	10
160024	40583	80082	11	80071	10	80071	30	320000	80010	20	80000	20	160000	1	160000	10
160024	40453	80011	11	80000	10	80000	30	320148	80047	20	80037	20	160000	1	160000	10
160024	40450	80011	11	80000	10	80000	30	320000	80010	20	80000	20	160000	1	160000	10
160024	40390	80011	11	80000	10	80000	30	320280	80080	20	80070	20	160138	1	160000	10

Test 5: throughput

Count: 16

Code:

  suqadd d0, d16
  suqadd d1, d16
  suqadd d2, d16
  suqadd d3, d16
  suqadd d4, d16
  suqadd d5, d16
  suqadd d6, d16
  suqadd d7, d16
  suqadd d8, d16
  suqadd d9, d16
  suqadd d10, d16
  suqadd d11, d16
  suqadd d12, d16
  suqadd d13, d16
  suqadd d14, d16
  suqadd d15, d16

Initialization

  movi v16.16b, 17

(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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
160204	80103	160107	101	160006	100	160010	300	640036	160108	200	160012	200	320028	1	160000	100
160204	80035	160107	101	160006	100	160010	300	640044	160110	200	160014	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640044	160110	200	160014	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320128	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320024	1	160000	100
160204	80035	160105	101	160004	100	160008	300	640036	160108	200	160012	200	320024	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 simd uop inputs (81)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
160024	80115	160017	11	160006	10	160010	30	640036	160018	20	160012	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640200	160062	20	160060	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10
160024	80035	160011	11	160000	10	160000	30	640000	160010	20	160000	20	320000	1	160000	10

SUQADD (scalar, 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: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations