Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNM (scalar, S)

Test 1: uops

Code:

  fminnm s0, s0, s1
  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)03191e3f4e51inst 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
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110001373216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110001073216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150126116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
1004203716006116872510001000100026468002018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnm s0, s0, s1
  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)030b1e3f4e51inst 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)72scheduler 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)9fa0a1a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150002041968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119856100001002003820038200382003820038
102042003715000611968725101001001000810010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150006591968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000010221657321161119791100001002003820038200382003820038
102042003715010611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150008061968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150001031968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010000019067101161119791100001002003820038200382003820038
1020420037150001241968725101001001000010010000500284768002001820037200371842273187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000003101177101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a6a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000306403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000306403163319785010000102003820038200382003820038
100242003715102081968725100481010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000306403163319785010000102003820038200382003820038
1002420085150043019687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100013006403163319785010000102003820038200382003820038
100242003715001451968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010001006403163319785010000102003820038200382003820038
100242003715002611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
100242003715001661968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010020006403163319785010000102003820038200382003820038
100242003715001681968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminnm s0, s1, s0
  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)03081e3f4e51inst 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)9fa0a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150002101968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100023156017101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000103196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010003375007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100210007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820083
102042003715000611968725101161001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150001891968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500082196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000101000640316221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000394196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500084196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371490084196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500162841968725100101010000101000050284768002001802003720037184443187671001020100002020000200372003711100211091010100001032000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371560084196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000608196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100200640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fminnm s0, s8, s9
  fminnm s1, s8, s9
  fminnm s2, s8, s9
  fminnm s3, s8, s9
  fminnm s4, s8, s9
  fminnm s5, s8, s9
  fminnm s6, s8, s9
  fminnm s7, s8, s9
  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)030a181e3a3f51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500001126258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051103161120035800001002003920039200392003920039
8020420038150000140258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000251101161120035800001002003920039200392003920039
8020420038150000161258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500012140258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
80204200381500001825258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000140258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
802042003815000017412580100100800001008000050064000020019200382003899737100228010020080096200160000200382003811802011009910010080000100210051101161120035800001002003920039200392003920039
8020420038150000140258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100003051101161120035800001002003920039200392003920039
8020420038150000140258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039
8020420038150000182258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030408090b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)dfe0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715000000000339258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022316222200350080000102003920039200392003920039
8002420038150000000001622580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100003203005022216222200350080000102003920039200392003920039
800242003815000000000139258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022216222200350080000102003920039200392003920039
80024200381500000000011023258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022216222200350080000102003920039200392003920039
800242003815000000000185258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022216222200350080000102003920039200392003920039
80024200381500000000012522580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100003303005022216322200350080000102003920039200392003920039
800242003815000000000283258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022216222200350080000102003920039200392003920039
800242003815000000000139258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022216222200350080000102003920039200392003920039
800242003815000000000160258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000100005022216222200350080000102003920039200392003920039
800242003815000000000139258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000000005022216222200350080000102003920039200392003920039