Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXNMP (vector, 2D)

Test 1: uops

Code:

  fmaxnmp v0.2d, v0.2d, v1.2d
  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)031e3f4e51inst 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073216111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100010073116111787100020382038203820382038
1004203715015616872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371536116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371508216872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716023216872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnmp v0.2d, v0.2d, v1.2d
  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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371490000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006934401031968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382008620038
10204200851500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307090a191e1f3a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020203502003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201018120200002003720037111002110910101000010000640316331978510000102003820038200382003820038
100242003715000000009121968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
100242003715000000001701968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnmp v0.2d, v1.2d, 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)030a0b1e1f3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968725101001001000010010000500284768002001820037200371842231876610100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150005370611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500060611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030408090b18191e1f3f4e51inst 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)6061696d6edispatch 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)9fa1a6a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000000611968725100101010000101000050284768010200542003720037184443187671001020100002020000200372003711100211091010100001000291864004164519785010000102003820038200382003820038
10024200371500000000264611968725100101010000101000050284768004200182003720037184443187671001020100002020000200372003711100211091010100001000427264044324419785010000102003820038200382003820038
1002420037150000000001208196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100054364004164319785210000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800020018200372003718444318767100102010168202000020037200371110021109101010000100043364043164419785010000102003820038200382003820038
100242008415000000000611968725100101010000101000050284768004200182003720037184448187671001020100002020000200372003711100211091010100001000366664043164419785010000102003820038200382003820038
1002420037150000000006119687251001010100001010000502851529102001820037200371844431876710010201000020200002003720037111002110910101000010001064004164419785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100030364004163419785010000102003820038200382003820038
10024200371500000000061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100048364004164419785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768004200182003720037184443187671001020100002020000200372003711100211091010100001000399064004164419785010000102003820038200382003820038
1002420037151000100006119687251001010100001010000502847680002001820037200371844431876710010201000020200002003720084111002110910101000010003916864003164319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnmp v0.2d, v8.2d, v9.2d
  fmaxnmp v1.2d, v8.2d, v9.2d
  fmaxnmp v2.2d, v8.2d, v9.2d
  fmaxnmp v3.2d, v8.2d, v9.2d
  fmaxnmp v4.2d, v8.2d, v9.2d
  fmaxnmp v5.2d, v8.2d, v9.2d
  fmaxnmp v6.2d, v8.2d, v9.2d
  fmaxnmp v7.2d, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03081e3a3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051103161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051101161120035800001002003920039200392003920039
8020420038150000230258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010020051101161120035800001002003920039200392003920039
802042003815010040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010013051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010099051101161120035800001002003920039200392003920039
802042003815000140258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051101161120035800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500391258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050208164620035080000102003920191200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050205166420035080000102003920039200392003920039
8002520038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050204164620035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000104050206166820035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000101050206168620035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050206167620035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000101050207165720048280000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050204164620035080000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050206167520035080000102003920039200392003920039
80024200381500514258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050206167820035080000102003920039200392003920039