Icestorm: FRSQRTS (vector, 4H) measurements

Code:

  frsqrts v0.4h, v0.4h, v1.4h

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	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000
1004	4033	1001	1	1000	1000	101557	1000	1000	2000	1	1000

Test 2: Latency 1->2

Code:

  frsqrts 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 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	20012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	313	1030662	10228	204	10161	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1029643	10162	200	10085	200	20012	1	10000	100
10204	40135	10115	103	10012	102	10062	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40135	10113	101	10012	100	10062	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1029657	10162	200	10084	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1029657	10162	200	10084	204	20778	3	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	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10025	40066	10025	21	10004	20	10030	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10

Test 3: Latency 1->3

Code:

  frsqrts 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	20012	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	1	10000	100
10204	40033	10101	101	10000	100	10000	300	1028557	10100	200	10004	200	20008	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	10006	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20092	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	1028557	10020	20	10000	20	20000	11	10000	10

Test 4: throughput

Count: 8

Code:

  frsqrts v0.4h, v8.4h, v9.4h
  frsqrts v1.4h, v8.4h, v9.4h
  frsqrts v2.4h, v8.4h, v9.4h
  frsqrts v3.4h, v8.4h, v9.4h
  frsqrts v4.4h, v8.4h, v9.4h
  frsqrts v5.4h, v8.4h, v9.4h
  frsqrts v6.4h, v8.4h, v9.4h
  frsqrts 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): 0.5004

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)
80204	40048	80108	101	80007	100	80011	300	320240	80159	200	80063	200	160028	1	80000	100
80204	40046	80107	101	80006	100	80010	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100
80204	40036	80105	101	80004	100	80008	300	320036	80108	200	80012	200	160024	1	80000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5004

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)
80024	40174	80029	21	80008	20	80012	68	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160000	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160138	11	80000	10
80024	40036	80021	21	80000	20	80000	65	320000	80020	20	80000	20	160130	11	80000	10

FRSQRTS (vector, 4H)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations