Apple M1 Microarchitecture Research by Dougall Johnson

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

FABS (vector, 2D)

Test 1: uops

Code:

  fabs v0.2d, 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)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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100007073116111786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000002473116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037211001100000073116111786100020382038203820382038
100420371606116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000001873116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000673116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fabs v0.2d, 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)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)9fa0a7a8a9cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500961196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037211020110099100100100001000000171011611197910100001002003820038200382003820038
102042003715002194196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001002000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000010071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197911100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000906119686251001010100001010000502847521120019200372003718443318767100102010000201000020037200371110021109101010000104000000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
100242003715000006119686251002210100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000100006402162219786010000102003820038200382003820038
1002420037150000053619686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
100242003715000006119686451002513100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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)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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150302925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039
8020420038150002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511801620035800001002003920039200392003920039

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)9facc5cficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915038125800101080000108000050640000412001920038200389996310018800102080000208000020038200381180021109101080000100150200416112008680000102003920039200392003920039
8002420038150939258001010800001080000506400004120019200382003899962510018800102080000208000020038200381180022109101080000100050202116112003580000102003920039200392003920039
8002420038150183925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200216222003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200216212003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200116112003580000102003920039200392003920039
800242003815033925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200116112003580000102003920039200392003920039
800242003815093925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050200116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050440116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050200116112003580000102003920039200392003920039