Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (vector, zero, 2D)

Test 1: uops

Code:

  fcmeq v0.2d, v0.2d, #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)0308090b18191e1f3f4e51inst 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)a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371600000120611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037160000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000002085073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038
10042037150000000611686251000100010002645211201820372037157131895100010001000203720371110011000000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq v0.2d, v0.2d, #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)030918191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000021019686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000104019686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000536196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001004807101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715010006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000012419686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715001261968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640716331978610000102003820038200382003820038
10024200371500611968625100101510000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
100242003715003611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006640316331978610000102003820038200382003820038
10024200371500821968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611964225100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
100242003715001561968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038
100242003715001261968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640316331978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmeq v0.2d, v8.2d, #0
  fcmeq v1.2d, v8.2d, #0
  fcmeq v2.2d, v8.2d, #0
  fcmeq v3.2d, v8.2d, #0
  fcmeq v4.2d, v8.2d, #0
  fcmeq v5.2d, v8.2d, #0
  fcmeq v6.2d, v8.2d, #0
  fcmeq v7.2d, v8.2d, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030f1e3f51inst 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)9fa8c2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150201342580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322008920038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000712580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000502580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)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)9fa6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150003925800101080000108000050640000200192003820038999603100188001020800002080000200382003811800211091010800001000000050201416572003533080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899960310018800102080000208000020038200382180021109101080000100100005020616572003516080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899960310018800102080097208000020101200381180021109101080000100000005020416511200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999603100188001020800002080000200382003811800211091010800001000060050201116411200350080000102003920039200392003920039
800242003815000704258001010800001080000506400002001920038200389996031001880010208000020800002003820038118002110910108000010000000502091635200350080000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200389996031001880010208000020800002003820038118002110910108000010000000502051656200350080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100000005020101610102003520080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100000005020516511200350080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100000005020516116200350080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899960310018800102080000208000020038200381180021109101080000100000005020416510200350080000102003920039200392003920039