Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (vector, zero, 8H)

Test 1: uops

Code:

  fcmge v0.8h, v0.8h, #0
  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)031e1f3f4e51inst 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
1004203715008416862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
10042037153908416862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160011016862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037154206116862510001000100026452102018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156906116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037152106116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037161506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge v0.8h, v0.8h, #0
  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)03191e1f3f4e51inst 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)9fa7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100010007101161119857100001002003820038200382003820038
10204200371510006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000307101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200852003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100025012307101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715001206119686251010010010000100100005002847521120018200372003718431318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000050019686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715001206119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000008011161119791100001002003820038200382003820038

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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100360640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010090640216221978610000102003820038200382003820038
100242003715024611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010610640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmge v0.8h, v8.8h, #0
  fcmge v1.8h, v8.8h, #0
  fcmge v2.8h, v8.8h, #0
  fcmge v3.8h, v8.8h, #0
  fcmge v4.8h, v8.8h, #0
  fcmge v5.8h, v8.8h, #0
  fcmge v6.8h, v8.8h, #0
  fcmge v7.8h, v8.8h, #0
  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)031e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010006011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010010011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e3f51inst 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)5f60696d6edispatch 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000502013168102003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020101612112003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000112001920038200389996310018800102080000208000020038200381180021109101080000100000502081612122003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000050207168102003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010010005020101610102003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020121610102003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020101610112003580000102003920039200392003920039
80024200381500000007042580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000050208161072003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000502071610102003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020121610102003580000102003920039200392003920039