Apple M1 Microarchitecture Research by Dougall Johnson

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

UABDL (vector, 4S)

Test 1: uops

Code:

  uabdl v0.4s, 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)03070a1e3a3f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723110268254825100010001000398313301830373037241532895100010002000303730371110011000002777416442630100030383038303830383038
100430372211026825482510001000100039831330183037303724153289510001000200030373037111001100000077416442630100030383038303830383038
1004303722111226825482510001000100039831330183037303724153289510001000200030373037111001100000077416442630100030383038303830383038
100430372311026825482510001000100039831330183037303724153289510001000200030373037111001100021077416442630100030383038303830383038
100430372211026825482510001000100039831330183037303724153289510001000200030373037111001100000077416442630100030383038303830383038
1004303722110268254825100010001000398313301830373037241532895100010002000303730371110011000005477416442630100030383038303830383038
1004303722110268254825100010001000398313301830373037241532895100010002000303730371110011000006677416442630100030383038303830383038
1004303723110268254825100010001000398313301830373037241532895100010002000303730371110011000006077416442630100030383038303830383038
100430372311026825482510001000100039831330183037303724153289510001000200030373037111001100000077416442630100030383038303830383038
100430372311026825482510001000100039831330183037303724153289510001000200030373037111001100000077416442630100030383038303830383038

Test 2: Latency 1->2

Code:

  uabdl v0.4s, 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)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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510252200100002002000030037300371110201100991001001000010000007101161129705100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000017101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372250000000004412954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000003006402162229630010000103003830038300383003830038
10024300372240000000005272954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000000000612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
10024300372240000000005362954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uabdl v0.4s, 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)0307080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731313001930085300372826532874510100200100002002000030037300371110201100991001001000010000000000071011612296340100001003003830038300383003830038
10204300372251100000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000028230071011611296340100001003008630038300383008530038
102043003722500001006742954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030073211611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010298500427731313001830037300372826532874510100204100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010020000000071011621296700100001003003830038300383003830038
10204300372250000000612954825101001171000810010000500427731313001830037300372826532876310100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722501100006129548251010010010000100100005004277313130018300853007428265328745101002001000020020000300373003711102011009910010010000100000000120071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000612953925101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
1020430037225000000030022954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3a3f4e51inst 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)60696b6d6edispatch 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)9fa1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243017822519001032954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000009006792163229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018030037300842828732876710010201000020200003003730037111002110910101000010001018606402162229630010000103003830085300383003830038
1002430037225087006129548251001010100001010000504277313030018030037300372828732876710158201000020200003003730037111002110910101000010000015006402162229630010000103003830038300383003830038
1002430037225000015102954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000005406402162229630010000103003830038300383003830038
100243003723201500612954825100101010000101000050427731303001803003730037282873287671001020100002020000300373003711100211091010100001000005106402162229630210000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001000109006692162229630010000103003830038300383003830038
1002430037225069007262954825100101010000101000050427731303001803003730037283053287671001020100002020000300843003711100211091010100001000480306402162229679010000103008530038300383003830038
10024300372240000126295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100055015306402162229692010000103003830061300383003830038
1002430037224000034029548251001010100001010000504277313130018330037300372828732876710010201000020200003003730037111002110910101000010005407806692162229630010000103008530038300383003830038
100243003722507200126295212510010101000010100005042773131300183300373003728287328767100102010000202000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uabdl v0.4s, v8.4h, v9.4h
  uabdl v1.4s, v8.4h, v9.4h
  uabdl v2.4s, v8.4h, v9.4h
  uabdl v3.4s, v8.4h, v9.4h
  uabdl v4.4s, v8.4h, v9.4h
  uabdl v5.4s, v8.4h, v9.4h
  uabdl v6.4s, v8.4h, v9.4h
  uabdl v7.4s, 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)033f51inst 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)60696b6d6edispatch 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015030258010810080008100800205006401320200200200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401320200200200392003999776999080120200800322001600642003920039118020110099100100800001001011151180160020036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
8020420039150611258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101162120036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040
802042003915041258010010080000100800005006400000200200200392003999733999780100200800002001600002003920039118020110099100100800001000000051101161120036800001002004020040200402004020040

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)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)9fa8acc2c5cdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815002412580010108000010800005064000002002020039200399996031001980010208000020160000200392003911800211091010800001000000502420161819200363680000102004020040200402004020040
80024200391500241258001010800001080000506400001200202003920039999603100198001020800002016000020039200391180021109101080000100000050241616179200362080000102004020040200402004020040
800242003915002412580010108000010800005064000012002020039200399996031001980010208000020160000200392003911800211091010800001000000502417161510200362080000102004020040200402004020040
800242003915002412580010108000010800005064000002002020039200399996031001980010208000020160000200392003911800211091010800001000000502416161516200362080000102004020040200402004020040
80024200391500241258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000050241316159200362080000102004020040200402004020040
800242003915002412580010108000010800005064000012002020039200399996031001980010208000020160000200392003911800211091010800001000010502414161315200362080000102004020040200402004020040
800242003915002412580010108000010800005064000012002020039200399996031001980010208000020160000200392003911800211091010800001003000502415161616200362080000102004020040200402004020040
80024200391500241258001010800001080000566400001200202003920039999603100198001020800002016000020039200391180021109101080000100000050241416161920036080000102004020040200402004020040
80024200391500241258001010800001080000506400000200202003920039999603100198001020800002016000020039200391180021109101080000100000050241516101620036080000102004020040200402004020040
80024200391500241258001010800001080000506400001200202003920039999603100198001020800002016000020039200391180021109101080000100000050241016161520036080000102004020040200402004020040