Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAX (scalar, D)

Test 1: uops

Code:

  fmax d0, d0, d1
  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)030818191e1f3a3f4e51inst 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)a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
1004203715000000611687251000100010002646801201820372037157231895100010002000203720371110011000000030073116111787100020382038203820382038
100420371600000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
100420371500000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038
1004203715000000611687251000100010002646800201820372037157231895100010002000203720371110011000000015073116111787100020382038203820382038
100420371500090061168725100010001000264680120182037203715723189510001000200020372037111001100000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmax d0, d0, d1
  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)03080b18191e1f3f4e51inst 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)9fa1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000009030071041611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611198250100001002003820038200382003820038
10204200371500000210726196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382008620038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000214071011611198270100001002003820086201322003820038
102042003715000000061196872510100100100001001000050028476800200182003720130184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000030071011611197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000540071011611197910100001002003820038200382003820038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371509611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715005651968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001047900640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371560611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010608502847680200182003720037184440318767100102010000202000020037200371110021109101010000104530640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmax d0, d1, d0
  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)03081e3f4e5051inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000143219687200212510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968702510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968702510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500012511968702510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061031968702510100100100001001000050028489631200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968702510100100100121001000059228476801200182003720084184223187451010020410000200200002003720037311020110099100100100001000071011611197910100001002003820038200382003820038
10204200371490061196870251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100011171011611197910100001002003820038200382003820038
102042003715000611968702510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000371011611197910100001002003820038200382003820038
102042003715000611968702510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000611968702510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284806612001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150011991968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150012491968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715004111968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382008520038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010300640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmax d0, d8, d9
  fmax d1, d8, d9
  fmax d2, d8, d9
  fmax d3, d8, d9
  fmax d4, d8, d9
  fmax d5, d8, d9
  fmax d6, d8, d9
  fmax d7, d8, d9
  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)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)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
80204200491504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051104162320035800001002003920039200392009220039
80204200381504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051103163320035800001002003920039200392003920039
80204200381504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103162320035800001002003920039200392003920039
802042003815010325801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103163220035800001002003920039200392003920039
80204200381504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103162320035800001002003920039200392003920039
802042003815010325801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051102162320035800001002003920039200392003920039
80204200381504025801001008000010080000500640000120019200382003899733999680100200800002001600002009820038118020110099100100800001000051103163320035800001002003920039200392003920039
802042003815056025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001051103163220035800001002003920039200392003920039
80204200381504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000051103163320035800001002003920039200392003920039
80204200381504025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001002051103163320035800001002003920039200392003920039

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)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)9fa8cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815004902580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020019167520035080000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100050200101610920035080000102003920039200392003920039
80024200381500288258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502005167720035180000102003920039200392003920039
8002420038150039258001010800001080000506407720200192003820038999631001880010208000020160000200382003811800211091010800001000502005165820035080000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502005168420035080000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502008168820035080000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000502008167520035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020081610720035080000102003920039200392003920039
80024200381500602580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071671020035080000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010005020071671020035080000102003920039200392003920039