Apple M1 Microarchitecture Research by Dougall Johnson

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

UQSUB (vector, 2S)

Test 1: uops

Code:

  uqsub v0.2s, v0.2s, v1.2s
  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)03073f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372326125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723016725482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723010525482510001000100039831313018303730372415328951000100020003037303711100110000673216222630100030383038303830383038
1004303723010325482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303722012425482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqsub v0.2s, v0.2s, v1.2s
  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)03191e3f4e51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250189612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
1020430037225002512954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
1020430037225007262954825101001001000010910000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500822954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731330018030037300372826532874510100200100002002000030037300371110201100991001001000010000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e3f4e51inst 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
1002430037224000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037224000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100002006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqsub v0.2s, v1.2s, v0.2s
  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)03090b1e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500072629548251010010010000100100005004277313300180300373008428265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500072629548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000143929548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722400044129548251010010010000100100005004277313300180300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500072629548251010010010000100100005004277313300180300373003728265328745101002001000020020000301333003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)72scheduler 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
1002430037281114706129548251001010100081010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500010329548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225012010329548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830085300383003830038
1002430037224012010329548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqsub v0.2s, v8.2s, v9.2s
  uqsub v1.2s, v8.2s, v9.2s
  uqsub v2.2s, v8.2s, v9.2s
  uqsub v3.2s, v8.2s, v9.2s
  uqsub v4.2s, v8.2s, v9.2s
  uqsub v5.2s, v8.2s, v9.2s
  uqsub v6.2s, v8.2s, v9.2s
  uqsub v7.2s, v8.2s, v9.2s
  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)03081e1f3a3f51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059151000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051105162320036800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051102162320036800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010003051102163220036800001002004020040200402004020040
80204200391500000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100040051103163320036800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010003051103163220036800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051102163320036800001002004020040200402004020040
8020420240150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010004051102162320036800001002004020040200402004020040
80204200391500000516258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010003051103163220036800001002004020040200402004020040
80204200391500000412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100029651102162320036800001002004020040200402004020040
8020420039150000041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051103163220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150004025800121080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010935020716422003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000105165020416242003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010305020416422003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000120020200392003999963100198001020800002016020820099200391180021109101080000103995020216242003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416422003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416242003680000102004020040200402004020040
8002420039150004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010305020416242003680000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001001535020416632003680000102004020040200402004020040