Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSUB (scalar, D)

Test 1: uops

Code:

  uqsub d0, d0, d1
  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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073216112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100001573116112630100030383038303830383038
100430372327612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372221612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000200030373037111001100007573116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqsub d0, d0, d1
  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)033f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372252512954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
10204300372257262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
10204300372253462954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010032627102162229634100001003003830038300383003830086
1020430037225612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010006007102162229634100001003003830038300833003830038
1020430037225612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010001007102162229634100001003003830038300383003830038
1020430037225612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
1020430037225612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
1020430037225612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010032007102162229634100001003003830038300383003830038
1020430037225612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007102162229634100001003003830038300383003830038
1020430037225612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010001007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2c3cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100002706006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000303006402162229630010000103003830038300383003830038
100243003722400000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000032015006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000044012006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006203006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100005809006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000433006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100003603006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000102001219496207673645229885410000103032230370303703036830416

Test 3: Latency 1->3

Code:

  uqsub d0, d1, d0
  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)030b18191e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000307101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000127101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100020107101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000307101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006404162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100106006402162429668010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100200006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqsub d0, d8, d9
  uqsub d1, d8, d9
  uqsub d2, d8, d9
  uqsub d3, d8, d9
  uqsub d4, d8, d9
  uqsub d5, d8, d9
  uqsub d6, d8, d9
  uqsub d7, d8, d9
  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)031e1f3f51inst 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)9fa6a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100020051103162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100071396051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102162220036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000081051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102162220036800001002004020040200402004020040
80204200391500041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100010051102162220036800001002004020040200402004020040

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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201716171720036180000102004020040200402004020040
800242003915004025800101080000108000050640000120020201142003999963100198001020800002016000020039200391180021109101080000100050201416171420036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201816141720036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201716171720036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201416171620036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010357850201416171420036080000102004020040200402004020040
800242003915006125800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201716141720036080000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502081617920036080000102004020040200402004020040
800242003915002302580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020171691720036080000102004020040200402004020040
800242003915004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201416171420036080000102004020040200402004020040