Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNMP (scalar)

Test 1: uops

Code:

  fminnmp d0, v0.2d
  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)033f4e51inst 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)a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000373116111786100020382038203820382038
1004203715821686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000003073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038
10042037156116862510001000100026452112018203720371571318951000100020002037203711100110000001273116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038
1004203715611686251000100010002645211201820372037157131895100010002000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnmp d0, v0.2d
  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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820083
10204200371500000061196862510100100100001001000050028475210200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000000726196862510100100100001001000050028475210200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475210200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715001000531196862510100100100001001000050028475210200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475210200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475211200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475210200182003720037184213187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000300103196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000006405162219786010000102003820038200382003820038
10024200371500000103196862510010101000010100005028475210200182003720037184453187671001020100002020000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500036061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500027061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500048061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001000006402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003711100211091010100001001006402162219786010000102003820038200382003820038
1002420037150100061196862510010101000010100005028475210200182003720037184433187671001020100002020000200372003751100211091010100001000006402162219786010000102003820038200382003820038
10024200371500039061196862510010101000010100005028475211200182003720037184433187671001020100002020000200372003711100211091010100001000496402162219786010000102003820038200382003820038
100242003715000165061196862510010101000010100005028475211200182003720037184433187671001020100002020000200372003711100211091010100001000036402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475211200182003720037184433187671001020100002020000200372003711100211091010100001000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fminnmp d0, v8.2d
  fminnmp d1, v8.2d
  fminnmp d2, v8.2d
  fminnmp d3, v8.2d
  fminnmp d4, v8.2d
  fminnmp d5, v8.2d
  fminnmp d6, v8.2d
  fminnmp d7, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03191e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500029258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
802042003815000504258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
8020420038150031529258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
80204200381500345300258010810080008100800205006401321200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
8020420038150036929258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220016006420038200381180201100991001008000010000011151181620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500049258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100050207166162003580000102003920039200392003920039
800242003815004353925800101080000108000050640000020019200382003899960310018800102080000201600002003820038118002110910108000010005020161616162003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100050206166162003580000102003920039200392003920039
80024200381500151392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502016161662003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502014161662003580000102003920039200392003920039
80024200381501039258001010800001080000506400000200192003820038999603100188001020800002016000020038200381180021109101080000100050206166132003580000102003920039200392003920039
8002420038150051392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502016161662003580000102003920039200392003920039
800242003815001839258001010800001080000506400001200192003820038999603100188001020800002016000020038200381180021109101080000100050206166162003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502016161662003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920192200389996031001880010208000020160000200382003811800211091010800001000502016166162003580000102003920100200392003920039