Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (zero, D)

Test 1: uops

Code:

  cmeq d0, d0, #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)03181e3f4e51inst 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
1004203715015611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq d0, d0, #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)03191e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150008419686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037149006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100006071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150008219686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000073511611197910100001002003820038200382003820038

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)9fa1cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371501686119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150126119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
10024200371502826119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715096119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmeq d0, d8, #0
  cmeq d1, d8, #0
  cmeq d2, d8, #0
  cmeq d3, d8, #0
  cmeq d4, d8, #0
  cmeq d5, d8, #0
  cmeq d6, d8, #0
  cmeq d7, d8, #0
  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)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)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)9fa0a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057151288292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151182162420035800001002003920039200392003920039
80204200381502671402580108100800081008002050064013202001920038200389977069989802202008013020080032200882009711802011009910010080000100001311151185163420035800001002003920039200392003920039
8020420038150363292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151183164320035800001002003920039200392003920039
8020420038150405292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100001011151183164320035800001002003920039200392003920039
8020420038150378292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100221011151184163220035800001002003920039200392003920039
802042003815048292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151183164320035800001002003920039200392003920039
802042003815054292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151183163420035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151184164320035800001002003920039200392003920039
8020420038150330292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151183164420035800001002003920039200392003920039
802042003815072292580108100800081008002050064013202001920038200389977069989801202008003220080032200382003811802011009910010080000100000011151184163420035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000000502013161152003580000102003920039200392003920039
800242003815000002707042580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050207165122003580000102003920039200392003920039
80024200381610000120392580010108000010800005064000012001920038200389996310018800102080000208000020038201131180021109101080000100000000050207165122003580000102003920039200392003920039
8002420038150000036039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020121611102003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020616672003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020416352003580000102003920039200392003920039
80024200381500000630392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050205165112003580000102003920039200392003920039
8002420038150000000602580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050206161152003580000102003920039200392003920039
800242003815000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020616662003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050204166112003580000102003920039200392003920039