Icestorm: FRECPE (vector, 4S) measurements

Code:

  frecpe v0.4s, v0.4s

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	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000
1004	4033	1001	1	1000	1000	50608	1000	1000	1000	1	1000

Test 2: Latency 1->2

Code:

  frecpe v0.4s, v0.4s

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	509608	10100	200	10006	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509771	10117	200	10032	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10006	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	1	10000	100
10204	40033	10101	101	10000	100	10000	300	509608	10100	200	10004	200	10004	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	509608	10020	20	10004	20	10006	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10032	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10
10025	40066	10025	21	10004	20	10017	70	509608	10020	20	10000	20	10000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10
10024	40033	10021	21	10000	20	10000	70	509608	10020	20	10000	20	10000	11	10000	10

Test 3: throughput

Count: 8

Code:

  frecpe v0.4s, v8.4s
  frecpe v1.4s, v8.4s
  frecpe v2.4s, v8.4s
  frecpe v3.4s, v8.4s
  frecpe v4.4s, v8.4s
  frecpe v5.4s, v8.4s
  frecpe v6.4s, v8.4s
  frecpe v7.4s, v8.4s

Initialization

  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 2.0004

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 ldst uop inputs (80)	map simd uop inputs (81)	? int output thing (e9)	? ldst retires (ed)	? simd retires (ee)	? int retires (ef)
80205	160070	80110	101	80009	0	100	80022	300	1999769	80100	200	80004	200	0	80033	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999769	80100	200	80004	200	0	80004	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999769	80100	200	80004	200	0	80004	1	0	80000	100
80205	160120	80123	101	80022	0	100	80046	300	1999769	80100	200	80004	200	0	80036	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999932	80122	200	80034	200	0	80004	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	2000028	80124	200	80036	200	0	80004	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999769	80100	200	80004	200	0	80034	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999769	80100	200	80004	200	0	80037	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999769	80100	200	80004	200	0	80004	1	0	80000	100
80204	160035	80101	101	80000	0	100	80000	300	1999769	80100	200	80004	200	0	80004	1	0	80000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 2.0004

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)
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80004	20	80032	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999932	80042	20	0	80032	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80025	160070	80030	21	80009	20	80022	0	70	0	1999769	80020	20	0	80000	20	80000	11	80000	10
80024	160035	80021	21	80000	20	80000	0	66	0	1999932	80042	20	0	80036	20	80000	11	80000	10

FRECPE (vector, 4S)

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: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations