Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSUB (scalar, H)

Test 1: uops

Code:

  sqsub h0, h0, h1
  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
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030633037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000200030373037111001100003073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230139254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100070073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqsub h0, h0, h1
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa1a6a7a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313130018030037300372826532874510100200100002062000030037300371110201100991001001000010000020007102162229634100001003003830038300383008130038
1020430037225006129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007102162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265328745101002001000020020000300373003711102011009910010010000100000105707102162229634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007102162229634100001003003830038300383003830038
1020430037225006129529251010010010008100100005004277313030018030037300372826532874510100200100002002000030037300371110201100991001001000010000010007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000104100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000030007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000010017102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010960640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010100640316332963010000103003830038300383003830038
10024300372250006129521251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010030640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250006129530251001010100001010000504277313130018030037300372828732876710010201000020200003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqsub h0, h1, h0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b191e3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500100825295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500000189295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000200007101161129634100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773130300643003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090a0b18191e1f3a3f4e51inst 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)696b6d6edispatch 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000101006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000103006403163329630010000103003830038300383003830038
100243003722500000000006129548831001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
100243003722500000000006129548251001010100001010000504277313300180300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqsub h0, h8, h9
  sqsub h1, h8, h9
  sqsub h2, h8, h9
  sqsub h3, h8, h9
  sqsub h4, h8, h9
  sqsub h5, h8, h9
  sqsub h6, h8, h9
  sqsub h7, h8, h9
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030918191e1f3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511041611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000622580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064082412002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
802042003915000000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000512712711200770800001002008920094201012004020102
80204201011501111321044125801001008000010080000500640000020020200392034999838100238021820080104202160210201002011721802011009910010080000100204755128125112007516800001002009020104200912010220094
8020420039150000002872580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040
8020420039150000120412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511011611200360800001002004020040200402004020040

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)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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815001295258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416442003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416432003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020516442003680000102004020040200402004020040
80024200391500103258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020416432003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416342003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416342003680000102004020040200402004020040
8002420039150040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020516432003680000102004020040200402004020040
8002420039150040258009010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020416442003680000102004020040200402004020040
80024200391500305258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020416442003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020416442003680000102004020040200402004020040