Apple M1 Microarchitecture Research by Dougall Johnson

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

FNEG (vector, 4H)

Test 1: uops

Code:

  fneg v0.4h, v0.4h
  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
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150010316862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715306116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150010516862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150011916862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fneg v0.4h, v0.4h
  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)03080b1e3a3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150006025119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003714900006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000006119686251010010510000100100005002847521020018020037200371842131874510100200100002001000020037200841110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000606119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000606119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715001006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100010206402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100010806402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
100242003715000330611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010007506402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
1002420037150000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
1002420037149000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006402162219786010000102003820038200382003820038
10024200371500000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010008106402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fneg v0.4h, v8.4h
  fneg v1.4h, v8.4h
  fneg v2.4h, v8.4h
  fneg v3.4h, v8.4h
  fneg v4.4h, v8.4h
  fneg v5.4h, v8.4h
  fneg v6.4h, v8.4h
  fneg v7.4h, v8.4h
  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)033f51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6dde0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420050150292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151185160200350800001002003920039200392003920039
8020420038150292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160200350800001002003920039200392003920039
80204200381502925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100004811151180160200350800001002003920039200392003920039
8020420038150502580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160200350800001002003920039200392003920039
80204200381502925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100009311151180160200350800001002003920039200392003920039
8020420038150504258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000010211151180160200350800001002003920039200392003920039
8020420038150292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010004011151180160200350800001002003920039200392003920039
8020420038150292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160200350800001002003920039200392003920039
8020420038150292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160200350800001002003920039200392003920039
80204200381502925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100009911151180160200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000003382580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000200050200008160001782003580000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000000502000017160001772003580000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200006160006172003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999627100188001020800002080000200382003811800211091010800001000001000502000014160001762003580000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000001020502000017160006172003580000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000090050200007160001762003580000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000001030502000081600019182003580000102003920039200392003920039
8002420038150000000004192580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050200006160001762003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002210910108000010000000005020000171600017172003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000990502000071600017172003580000102003920039200392003920039