Apple M1 Microarchitecture Research by Dougall Johnson

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

FABS (scalar, H)

Test 1: uops

Code:

  fabs h0, h0
  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)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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371601261168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371600611686251000100010002645211201820372037157131895100010001000203720371110011000011873116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100002073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150361168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500141168625100010001000264521120182037203715713189510001168100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fabs h0, h0
  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)03081e3f4e51inst 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)60696b6d6edispatch 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968625101001001000010010000500284752102001802003720037184213187451010020010000200100002003720037111020110099100100100001000307101161119791100001002003820038200382003820038
102042003714900611968625101001001000010010000500284752102001802003720037184213187451010020010000200100002003720037111020110099100100100001000907101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010006307101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500246119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010002107101161119791100001002003820038200382003820038
1020420037150036611968625101001001000010010000500284752102001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200180200372003718421318745101002001000020010000200372003711102011009910010010000100128407101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010011807101161119791100001002003820038200382003820038
1020420037150001611968625101001001000010010000500284752102001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)60696b6d6edispatch 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196862510010101001210100005028475211200180200372003718443031876710010201000020100002003720037111002110910101000010000000205006612162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150100000061196862510010101000010100005028475211200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000000107196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820085200382003820038
10024200371500000000124196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010040000606402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475210200180200372003718443031876710010201000020100002003720037111002110910101000010000020006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475211200180200372003718443031876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fabs h0, h8
  fabs h1, h8
  fabs h2, h8
  fabs h3, h8
  fabs h4, h8
  fabs h5, h8
  fabs h6, h8
  fabs h7, h8
  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)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)9facc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
802042003815002925801081008000810080108500640132020019200382003899861210013801202008013320080032200382003811802011009910010080000100011151180550020035800001002003920039200392009320039
8020420038150929258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
8020420038150071258010810080008100800205006401320200562003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
80204200381502429258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180460020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100801125006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090a0b18191e1f3f51inst 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)60696b6d6edispatch 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000003003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050202164420035080000102003920039200392003920039
8002420038150000100903925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
8002420038150000000181326025800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050203164420035080000102003920039200392003920039
80024200381500000000022925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050202164220035080000102003920039200392003920039
80024200381500000002403925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050204162420035080000102003920039200392003920039
80024200381500000001503925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050202164420035080000102003920039200392003920039
80024200381500000008403925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050204164220035080000102003920039200392003920039
800242003815000000010806225800101080000108009650640000020019020038200389996310018800102080000208000020038200381180021109101080000100000000050205164220035080000102003920039200392003920039