Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64X (scalar, D)

Test 1: uops

Code:

  frint64x d0, d0
  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)0318191e1f3f4e51inst 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
100430372400306125472510001000100039816003018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
100430372300008125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372400006125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723003006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000025125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230124061254725100010001000398160130183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
100430372400006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724001206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64x d0, 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)0308090b18191e3a3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200000008229547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037241000001206129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043008523200011006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037232000000015629547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160300183300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723200000006129547251010010010000100100005004277160300180300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038

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)9e9fa6a8a9acc5cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037243006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006404160652962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160462962910000103003830038300383008530038
1002430037224006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160662962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160662962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160562962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010010006405160652962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006405160652962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160562962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160442962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000010000006406160652962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64x d0, d8
  frint64x d1, d8
  frint64x d2, d8
  frint64x d3, d8
  frint64x d4, d8
  frint64x d5, d8
  frint64x d6, d8
  frint64x d7, d8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03041e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391551030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391560072258010810080008100800205006407881200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391560058258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100031115118016020036800001002004020040200402004020040
802042003915501251258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391600030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016120036800001002004020099200402004020040
802042003915500128525801081008000810080020500640132020020200392003999771510015801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391560053258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100201115118016020036800001002004020040200402004020040

1000 unrolls and 10 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)9fa0a6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000124258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020616652003680000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100001205020516662004880000102004020040200402004020040
8002420039155000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020716772003680000102004020040200402004020040
8002420039155000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020716662004680000102004020040200402004020092
8002420039156014400105258001010800001080000506408120200812015120039999631001980010208000020800002003920039118002110910108000010000005020716772003680000102004020040200402004020040
8002420039156012880785258001010800971080000506400000200202009620093999681001980010208000020800002003920039118002110910108000010000005020716772003680000102004020040200402004020040
80024200391550000727258001010800001080000506400001200202003920039999631001980010208042320800002003920240118002110910108000010001605020716762004780000102004020040200402004020040
8002420039155000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020616662004680000102004020040200402004020040
8002420039155000178425800101080000108000050640812020020200392003999967100198001020800002080000200922003911800211091010800001020199105020816772003680000102004020040200402004020040
80024200391560000916258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020616662004680000102004020040200402004020040