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, 8H)

Test 1: uops

Code:

  fneg v0.8h, v0.8h
  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)03081e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111787100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fneg v0.8h, v0.8h
  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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715004691968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715001051968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010035015071011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010010012671011611197910100001002003820038200382003820038
10204200371500611968663101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715001991968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500145196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001002704871011611197910100001002003820038200382003820038
102042003715002821968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)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
1002420037150006401968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010340640216221978610000102003820038200382003820038
100242003715006126196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150001241968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010280640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216321978610000102003820038200382003820038
1002420037150001080196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003714900611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010350640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010380640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fneg v0.8h, v8.8h
  fneg v1.8h, v8.8h
  fneg v2.8h, v8.8h
  fneg v3.8h, v8.8h
  fneg v4.8h, v8.8h
  fneg v5.8h, v8.8h
  fneg v6.8h, v8.8h
  fneg v7.8h, v8.8h
  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)031e1f3f51inst 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420047150002012580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151183160120103800001002003920039200392003920039
8020420038150008772580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150008212580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150005412580108100800081008002050064090020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150009582580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500010872580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042008815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000732580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010003214711151180160020035800001002003920039200392003920039
802042003815000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010002715011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a0b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd0d2icache miss (d3)d5d6d9daddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000006812580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000003050200001116001516200350080000102003920039200392003920039
80024200381590000000016092580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001516001313200350080000102003920039200392003920039
8002420038150000000001392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001516001212200350080000102003920039200392003920039
8002420038150000000001392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001416001414200350080000102003920039200392003920039
800242003815000000000133225800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100005703050200001316001316200350580000102003920039200392003920039
800242003815000000000111522580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001116001613200350080000102003920039200392003920039
80024200381500000000016782580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001416001212200350080000102003920039200392003920039
8002420038150000000393011672580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001716001216200830080000102003920039200392003920039
8002420038150000000001392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000050200001116001511200350080000102003920039200392003920039
8002420038150000000001392580010108000010800005064000011200192003820038999631001880010208000020800002003820038118002110910108000010000300050200001416001115200350080000102003920039200392003920039