Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FMAXNMP (vector, 2S)

Test 1: uops

Code:

  fmaxnmp v0.2s, v0.2s, v1.2s
  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

retire (01)cycle (02)03081e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150246116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715066116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715106116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150031916872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnmp v0.2s, v0.2s, v1.2s
  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

retire (01)cycle (02)030818191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968743101001141000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371500003000611966725101001001000010310000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
10204200371500000002511968725101001001000010010150500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000106402162219785010000102003820038200382003820038
1002420037150100611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000066402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010002406402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000201792003711100211091010100001000001776402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000036402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000036402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000136402162219785010000102003820038200382003820038
10024200371500120611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000066402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000011656402162219785010000102003820038200382003820038
10024200371500120611968725100101010000101000050284768002001820037200371845431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnmp v0.2s, v1.2s, v0.2s
  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

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715005681968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715006121968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150154321968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000327101161119791100001002003820038200382003820038
102042003715001051968725101001001000010010000500284768012001820084200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715001051968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371490611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715006081968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000001681968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101015271284896312001820037200371844431876710010201000020200002003720037111002110910101000010000640232221978510000102003820038200382003820038
1002420037150000001031968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102008620086200852008620038
10024200371500010598611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000211326119687251001010100001010000502847680120018200372003718444251876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150000001141968725100101010000101000060284768012001820037200371844431876710010201000020200002003720037111002110910101000010003640216321978510000102003820038200852003820038
100242003715010000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102008620085200382003820038
10024200371500004080611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnmp v0.2s, v8.2s, v9.2s
  fmaxnmp v1.2s, v8.2s, v9.2s
  fmaxnmp v2.2s, v8.2s, v9.2s
  fmaxnmp v3.2s, v8.2s, v9.2s
  fmaxnmp v4.2s, v8.2s, v9.2s
  fmaxnmp v5.2s, v8.2s, v9.2s
  fmaxnmp v6.2s, v8.2s, v9.2s
  fmaxnmp v7.2s, v8.2s, v9.2s
  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): 0.2505

retire (01)cycle (02)03193f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815001872580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100030051103161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008011250064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815003272580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100001051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8acc2c5cfd2icache miss (d3)d5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031602320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031602320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200021603320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031603320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031603320035080000102003920039200392003920039
8002420038150000000602580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000150200021602320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000102000000050200031602320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031602320035080000102003920039200392003920039
80024200381500000120392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031602320035080000102003920039200392003920039
8002420038150000000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200031603320035080000102003920039200392003920039