Firestorm: UXTL (4S) measurements

Code:

  uxtl v0.4s, v0.4h

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: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	2037	16	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	3	16	1	1	1854	1000	2038	2038	2038	2038	2038
1004	2037	16	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2086	2038
1004	2037	16	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	2	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	0	233	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	1	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038

Test 2: Latency 1->2

Code:

  uxtl v0.4s, 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): 2.0037

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	51	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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	20037	155	0	0	0	0	0	0	0	0	0	145	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	3	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	0	0	84	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	156	0	0	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	0	0	103	19686	25	10100	100	10000	100	10000	500	2848785	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	12	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	0	0	831	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	0	0	0	0	0	0	110	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	1e	3f	4e	51	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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	20037	156	0	0	214	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	103	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	0	1724	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	0	251	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	19786	0	10000	10	20038	20085	20038	20038	20038

Test 3: throughput

Count: 8

Code:

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

Initialization

  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	51	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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80204	20038	156	0	0	0	0	0	0	0	599	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	156	0	0	0	0	0	0	0	519	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	156	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	141	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80172	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	59	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	599	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	mmu table walk data (08)	09	l2 tlb miss data (0b)	0f	18	19	1e	1f	3a	3f	51	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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20039	155	0	0	0	0	0	0	0	0	0	0	81	25	80010	10	80000	10	80000	50	640000	0	20135	20239	20244	9996	22	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	2	0	1	2	2048	0	5110	0	0	4	76	4	1	3	20229	0	80000	10	20296	20290	20287	20237	20290
80024	20287	157	0	1	0	1	0	5	5	669	352	1	1933	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	2	5092	0	0	3	59	0	1	3	20307	0	80000	10	20239	20238	20288	20291	20240
80024	20239	157	0	1	0	0	0	4	5	672	352	0	67	142	80480	10	80467	10	80580	50	641548	0	20057	20284	20292	10038	26	10127	80600	20	80584	20	80585	20288	20286	3	1	80021	10	9	10	10	80000	10	2	2	2	0	0	4	2325	0	5125	0	0	2	70	0	2	2	20229	0	80000	10	20338	20293	20294	20290	20345
80024	20291	157	2	0	0	1	0	5	6	669	440	0	3244	25	80010	10	80000	10	80000	50	640000	1	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	2	0	0	0	5089	0	0	1	88	2	1	2	20154	0	80000	10	20350	20338	20288	20337	20380
80024	20343	158	0	0	0	0	0	3	6	936	616	0	3184	159	80753	10	80564	10	80585	50	644616	1	20212	20388	20399	10056	39	10202	80693	20	80779	20	80680	20391	20391	8	1	80021	10	9	10	10	80000	10	0	0	0	2	0	0	3278	0	5020	0	0	1	16	0	1	1	20035	0	80000	10	20039	20039	20039	20089	20193
80024	20288	157	0	1	0	1	0	3	5	660	528	0	1616	25	80010	10	80000	10	80000	50	640000	1	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	2	1178	0	5140	0	0	2	86	0	1	1	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	0	0	0	0	0	792	176	0	1207	138	80290	10	80562	10	80486	50	640768	0	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	2325	0	5020	0	0	1	16	2	9	4	20035	1	80000	10	20292	20243	20343	20394	20451
80024	20141	162	0	1	0	1	0	8	4	1056	440	0	1663	142	80290	10	80560	10	80194	50	646210	0	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	2	0	0	0	0	0	470	0	5020	0	0	1	16	0	1	1	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	160	0	0	0	0	0	0	0	0	0	0	39	25	80010	10	80000	10	80000	50	640000	1	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	0	5020	0	0	1	16	0	1	1	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	0	0	0	0	0	0	0	0	39	25	80010	10	80000	10	80000	50	640000	1	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	0	5020	0	0	1	16	0	1	1	20035	0	80000	10	20039	20039	20039	20039	20039

UXTL (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