Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSUB (vector, 8H)

Test 1: uops

Code:

  sqsub 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)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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
10043037225161254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038
10043037231861254825100010001000398313130183037303724153289510001000200030373037111001100073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqsub 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)03080b1e1f3f4e51inst 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)6061696d6edispatch 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)9fa8cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722400006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722501906129548251010010010000100100005004277313153005430037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313153001830037300372826532874510100200100002002000030037300371110201100991001001000010007105111611296340100001003003830038300383003830038

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)9fa0a6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006405163329630010000103003830038300383003830038
1002430037225000000822954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
100243003722400006510612954825100101010000101000050427731303001830084300842828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037224000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037224000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000066403163329630010000103003830038300383003830038
10024300372250000009122954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000006403163329630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqsub 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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000001350071021622296340100001003003830038300383003830038
1020430037225000000007262954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000001680071021622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000060171021622296340100001003003830038300383003830038
10204300372250000000072629548251010010010000100100005004277313130054300373003728265328745101002001000020020000300373003711102011009910010010000100000060071021622296340100001003003830038300383003830038
10204300372250000000025129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000030071021622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000030071021622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000030071021622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000000071021622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000870071021622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000030071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954843100221010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037211002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010003640216222963010000103003830038300383003830038
100243003722500000612954825100101010008101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqsub v0.8h, v8.8h, v9.8h
  sqsub v1.8h, v8.8h, v9.8h
  sqsub v2.8h, v8.8h, v9.8h
  sqsub v3.8h, v8.8h, v9.8h
  sqsub v4.8h, v8.8h, v9.8h
  sqsub v5.8h, v8.8h, v9.8h
  sqsub v6.8h, v8.8h, v9.8h
  sqsub 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)0308090b191e3f51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051102161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001001806051101161120036800001002004020040200402004020040
802042003915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
802042003915000000416680204116800981058010462664081612002020039200399973399978010020080098200160198200982009821802011009910010080000100492521051281161120036800001002004020040200402004020040
80204200391501100026825801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001002609051101161120036800001002004020040200402004020040
80204200391500000370625801001008000010180000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001001903051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001005603051101161120036800001002004020040200402004020040
802042003915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040
8020420039150000004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001003203051101161120036800001002004020040200402004020040
802042003915000000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3a3f51inst 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)6061696d6edispatch 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)9fa1a6a8a9accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000040258001010800001080000506400000020020200392003999963100198001020800002016000020039200391180021109101080000100020035020005162420036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010000005020502162420036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010002005020003163420036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010002005020004162420036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000052002020039200399996310019800102080000201600002003920039118002110910108000010001005020002164220036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010000005020504164220036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000052002020039200399996310019800102080000201600002003920039118002110910108000010001005020004162420036080000102004020040200402004020040
80024200391500000051525800101080000108000050640000052002020039200399996310019800102080000201600002003920039118002110910108000010003035020004162420036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010000005020004164220036080000102004020040200402004020040
8002420039150000004025800101080000108000050640000052002020039200399996310019800102080000201600002003920039118002110910108000010002005020004164220036080000102004020040200402004020040