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, 8H)

Test 1: uops

Code:

  fabs v0.8h, v0.8h
  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)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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182073203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100006073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715961168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fabs v0.8h, v0.8h
  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)030818191e1f3a3f4e51inst 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)9fa0a1a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000061196862510100100100001001000050028475211020018200372003718421318745101002001000020010000200372003711102011009910010010000100000090710011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475210020018200372003718421318745101002001000020010000200372003711102011009910010010000100000093710011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521002001820037200371842131874510100200100002001000020037200371110201100991001001000010000009710112511197910100001002003820038200382003820038
1020420037150000000103196862510100100100001001000050028475211120018200372003718421318745101002001000020010000200372003711102011009910010010000100000090710011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475210020065200372003718421318745101002001000020010000200372003711102011009910010010000100000072710011611197910100001002003820038200382003820038
10204200371500000006119686251010010010000100100005002847521002001820037200371842131874510100200100002001000020037200371110201100991001001000010000000710011611197910100001002003820038200382003820038
10204200371500000002321968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000102710011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475210020018200372003718421318745101002001000020010000200372003711102011009910010010000100000093710011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475210120018200372003718421318745101002001000020010000200372003711102011009910010010000100000072710011611197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000105710011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307191e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640316221978610000102003820038200382003820038
10024200371500008219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000103430640216221978610000102003820038200382003820038
100242003715000072619686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000102030640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102008620085200382008520038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201018020100002003720037111002110910101000010002640216221978610000102003820038200382003820038
10024200371500036119686251001010100001010000502847521120018200372003718455318767100102010000201000020037200371110021109101010000102600640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010200640216221978610000102003820038200382003820038
100242003715003061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001037810640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820085200382003820038
1002420037150000611968644100101010000101000050284752102001820037200371844331878610010201000020100002003720037111002110910101000010100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fabs v0.8h, v8.8h
  fabs v1.8h, v8.8h
  fabs v2.8h, v8.8h
  fabs v3.8h, v8.8h
  fabs v4.8h, v8.8h
  fabs v5.8h, v8.8h
  fabs v6.8h, v8.8h
  fabs v7.8h, v8.8h
  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)030b3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151184160020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010010011151180160020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002005020050200492004920050
8020420048150064278011610080016100800285006401961200282004820048997699986801282008003820080038200482004811802011009910010080000100270322251281231120046800001002005020049200492004920050
8020420048150064278011610080016100800285006401960200282004920048997610998680128200800382008003820048200491180201100991001008000010010322251281231120045800001002005020049200492004920049
8020420048150164268011610080016100800285006401960200282004820048997610998680128200800382008003820048200481180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150040925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010010911151180160020035800001002003920039200392003920039
8020420038150021925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000311151180160020035800001002003920039200392003920039

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)9fa8acc2cfd0d2d5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000030136025800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
8002420038150000000113425800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001003050200021600222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050200021600222003580000102003920039200392003920039
80024200381500000004525800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001003050200021600222003580000102003920039200392003920039