Apple M1 Microarchitecture Research by Dougall Johnson

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

SQADD (vector, 4H)

Test 1: uops

Code:

  sqadd v0.4h, v0.4h, v1.4h
  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)03090b191e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000373116112630100030383038303830383038
1004303722000010325482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383085
100430372300008225482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722000015125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300008225482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200006125482510001000100039831330183037303724153289510001000200030373037111001100010073116112630100030383038303830383038
100430372300006125482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722000014925482510001000100039831330183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqadd v0.4h, v0.4h, v1.4h
  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)031e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000042001369295482510010101000810100005042773131300543003730037282873287671001020100002020000300373003711100211091010100001000000306406164429630010000103003830038300863003830133
100243003722500002000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165529630010000103003830038300383003830038
100243003722500000000161295482510010101000010100005042773131300183018030037282873287671001020100002020000300373003711100211091010100001000000006404165629630010000103003830038300383003830038
100243003722500000000061295482510010101000011101495042800270300183003730037282963287671001020100002020000300373003711100211091010100001000000006405496429630010000103003830038300383003830085
10024300372250000001200103295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003721100211091010100001000000306405165629630010000103003830038300383003830038
10024300372250000001200103295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165529630010000103003830038300383003830038
1002430037225000000000103295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000010325306405165529630010000103003830038300383003830038
100243003722500000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006405166629630010000103003830038300383003830038
100243003722500000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405515629630010000103003830038300383003830038
100243003722500000000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000220006405165629630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqadd v0.4h, v1.4h, v0.4h
  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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007100116112963425100001003003830038300383003830038
1020430037225000000061295482510125100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000806011611296340100001003003830038300383003830038
1020530037225000000061295482510100100100081001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000714021722296340100001003003830038300383003830038
1020430037225000000161295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000710011611296340100001003003830038300853003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000007120116212963425100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100090640316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100253003722406129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225020829548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000101000640216222963010000103003830038300383003830038
1002430037225396129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372251866129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222967210000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqadd v0.4h, v8.4h, v9.4h
  sqadd v1.4h, v8.4h, v9.4h
  sqadd v2.4h, v8.4h, v9.4h
  sqadd v3.4h, v8.4h, v9.4h
  sqadd v4.4h, v8.4h, v9.4h
  sqadd v5.4h, v8.4h, v9.4h
  sqadd v6.4h, v8.4h, v9.4h
  sqadd v7.4h, v8.4h, v9.4h
  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)030b1e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511041633200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511021623200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511021623200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
80204200391500062258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511031632200360800001002004020040200402004020040
80204200391500041258010010080098100800005006400002002002003920039997339997801002008000020016000020039200391180201100991001008000010000511021623200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa0a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500013525800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100035020016161782003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020017168172003680000102004020040200402004020040
800242003915000822580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010600502006361782003680000102014120099200402004020040
800242008915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000502008161762003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502008168172003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100035020017167172003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020061200392003999963101288001020800002016000020039200391180021109101080000100005020017168172003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020061617172003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000502008161782003680000102004020040200402004020040
80024200391500051525800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020017161782003680000102004020040200402004020040