Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDP (scalar)

Test 1: uops

Code:

  addp d0, v0.2d
  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)031e3a3f4e51inst 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)a8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
10042037154506116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000200020372037111001100020730216221786100020382038203820382038
1004203715906116862510001000100026452120182037203715713190710001000200020372037111001100000730216221786100020382038203820382038
10042037159606116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
1004203716006116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038
1004203716006116862510001000100026452120182037203715713189510001000200020372037111001100000730216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  addp d0, 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715806119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119675251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820085200382003820038
10204200371500610196862510100100100001001000050028475211200182003720037184213187451010020010000200200002003720037111020110099100100100001003007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100207101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000906119686451001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006403162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000008219686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402163219786010000102003820038200382003820038
10024200371500000000174019686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000010006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037150000000076819686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
1002420037151000000012619686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038
10024200371500000000135319686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  addp d0, v8.2d
  addp d1, v8.2d
  addp d2, v8.2d
  addp d3, v8.2d
  addp d4, v8.2d
  addp d5, v8.2d
  addp d6, v8.2d
  addp d7, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030818191e3f51inst 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)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151182162120035800001002003920039200392003920039
802042003815000004322580108100800081008002050064013212001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151182161220035800001002003920039200392003920039
802042003815000167462580108100800081008002050064013212001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151181161220035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151181161220035800001002003920039200392003920039
802042003815000008242580108100800081008002050064013202001920038200389977699898012020080032200160064200382003811802011009910010080000100030611151181161220035800001002003920039200392003920039
802042003815000001702580108100800081008002050064013202001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151181162220035800001002003920039200392003920039
80204200381500000942580108100800081008002050064013212001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151182162120035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151181162220035800001002003920039200392003920039
80204200381500000522580108100800081008002050064013212001920038200389977699898012020080032200160064200382003811802011009910010080000100000011151182162120035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200160064200382003811802011009910010080000100020311151181161220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3a3f51inst 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)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500010812580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100100502016167122003580000102003920039200392003920039
80024200381500124184258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000050201116852003580000102003920039200392003920039
800242003815000239258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000050209166112003580000102003920039200392003920039
8002420038150024225725800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001020468050201016582003580000102003920039200392003920039
80024200381500026025800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000005020716992003580000102003920039200392003920039
80024200381500028125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000005020816572003580000102003920039200392003920100
8002420038150002392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100100502010161072003580000102003920039200392003920039
80024200381500023925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000005020716742003580000102003920039200392003920039
80024200381500023925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000005020716952003580000102003920039200392003920039
800242003815000239258001010800001080000506400002001920038200389996310018800102080132201600002003820038118002110910108000010000050205167102003580000102003920039200392003920039