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, 8H)

Test 1: uops

Code:

  sqadd v0.8h, v0.8h, v1.8h
  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)030b1e3f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254825100010001000398313030183037303724153289510001000200030373037111001100000073316112630100030383038303830383038
10043037230061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230061254825100010001000398313130183037303724153289510001000200030373037111001100002373116112630100030383038303830383038
100430372202461254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230082254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100020003037303711100110000013273116112630100030383038303830383038
10043037230061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037220061254825100010001000398313130183037303724153289510001000200030373037111001100001373116112630100030383038303830383038
10043037230061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqadd v0.8h, v0.8h, v1.8h
  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)031e3a3f4e51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773130300183003730037282727287411010020010008200200163003730037111020110099100100100001000001117180160029646100001003003830038300383003830038
102043003722521061295482510100100100001001000050042773130300183003730037282727287401010020010008200200163003730037111020110099100100100001000001117170160029647100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282727287411010020010008200200163003730037111020110099100100100001000001117180160029646100001003003830038300383003830038
102043003722536061295482510100100100001001000050042773130300183003730037282726287411010020010008200200163003730037111020110099100100100001000001117180160029647100001003003830038300383003830038
102043003722518061295482510100100100001001000050042773131300183003730037282726287401010020010008200200163003730037111020110099100100100001000001117170160029646100001003003830038300383003830038
102043003722530061295482510100100100001001000050042773130300183003730037282726287411010020010008200200163003730037111020110099100100100001000001117170160029647100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282726287411010020010008200200163003730037111020110099100100100001000001117180160029646100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282726287401010020010008200200163003730037111020110099100100100001000001117170160029646100001003003830038300383003830038
102043003722524061295482510100100100001001000050042773130300183003730037282727287401010020010008200203603003730037111020110099100100100001000001107101161129634100001003003830038300383003830038
102043003722524061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010001640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225150612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010030640216222963010000103003830038300383003830038
1002430037224330612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372253002512954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372253000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225180612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225210612954825100101010000101014850427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372243120612954825100101010000101000050427731313001830037300372828732876710010201000020203263003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqadd v0.8h, v1.8h, 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): 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007102161129634100001003003830038300383003830038
1020430037225186129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225186129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225546129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722596129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225186129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225156129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225336129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225216129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722517461295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372245461295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372252761295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295302510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqadd v0.8h, v8.8h, v9.8h
  sqadd v1.8h, v8.8h, v9.8h
  sqadd v2.8h, v8.8h, v9.8h
  sqadd v3.8h, v8.8h, v9.8h
  sqadd v4.8h, v8.8h, v9.8h
  sqadd v5.8h, v8.8h, v9.8h
  sqadd v6.8h, v8.8h, v9.8h
  sqadd v7.8h, v8.8h, v9.8h
  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)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)696d6edispatch 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)9fa0a1a6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500000480412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511041632200360800001002004020040200402004020040
8020420039150000090412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000001000511021632200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200402004020040
80204200391500000480412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000030511031633200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000001000511031632200360800001002004020040200402004020040
8020420039150000090412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200402004020040
8020420039150000000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000000511031633200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391509040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100050207161192003680000102004020040200402004020040
80024200391500040258001010800001080000506400001120020200392003999963100198001020800002016000020039200391180021109101080000100050209166112003680000102004020040200402004020040
800242003915039904025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020111612122003680000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502011161172003680000102004020040200402004020040
80024200391504830402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502010168112003680000102004020040200402004020040
80024200391500040258001010800001080000556408280020020200392003999963100198001020800002016000020039200391180021109101080000100050201216972003680000102004020040200402004020040
8002420039150004025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010005020111612122003680000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502012168132003680000102004020040200402004020040
800242003915012023025800101080000108000050640000002002020039200399996310019800102080000201600002003920039118002110910108000010205020101611102003680000102004020040200402004020040
800242003915030402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000502091612112003680000102004020040200402004020040