Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

ASR (register, 64-bit)

Test 1: uops

Code:

  asr x0, x0, x1
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

retire uop (01)cycle (02)03mmu table walk instruction (07)1e3f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)606d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst int alu (97)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
10041035800618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
10041035700618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
100410357006186225100010001000169160103510357283868100010002000103541111001100002773141119371000100010361036103610361036
10041035800618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
10041035800618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
10041035700618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
10041035806618622510001000100016916010351035728386810001000200010354111100110000073141119371000100010361036103610361036
100410358002438622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
100410358084618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036
10041035700618622510001000100016916110351035728386810001000200010354111100110000073141119371000100010361036103610361036

Test 2: Latency 1->2

Code:

  asr x0, x0, x1
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)03l2 tlb miss data (0b)1e1f3f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
1020410035750008298772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035750008498772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
10204100357500078698772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035760006198772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035750008498772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035750008498772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035750006198772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035750006198772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000001071013711994110000101001003610036100361003610036
1020410035750006198772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036
1020410035750006198772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010000000071013711994110000101001003610036100361003610036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)033f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)60696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
1002410035751039863251001010010100108878404969551003510035860238740100101002020020100354111100211091010010100064044165994010000100101003610036100361003610036
100241003575619863251001010010100108878414969551003510035860238740100101002020020100354111100211091010010100064064174994010000100101003610036100361003610036
1002410035756198632510010100101001088784049695510035100358602387401001010020200201003541111002110910100101001264064166994010000100101003610036100361003610036
10024100357547098632510010100101001088784149695510035100358602387401001010020200201003541111002110910100101001564054153994010000100101003610036100361003610036
1002410035751919863251001010010100108878414969551003510035860238740100101002020020100354111100211091010010100064054164994010000100101003610036100361003610036
100241003575619863251001010010100108878414969551003510035860238740100101002020020100354111100211091010010100064064154994010000100101003610036100361003610036
10024100357514798632510010100101001088784049695510035100358602387401001010020200201003541111002110910100101071564064164994010000100101003610036100361003610036
1002410035751829863251001010010100108878404969551003510035860238740100101002020020100354111100211091010010100064054167994010000100101003610036100361003610036
1002410035751249863251001010010100108878404969551003510035860238740100101002020020100354111100211091010010100064054166994010000100101003610036100361003610036
10024100357514298632510010100101001088784049695510035100358602387401001010020200201003541111002110910100101001864064175994010000100101003610036100361003610036

Test 3: Latency 1->3

Code:

  asr x0, x1, x0
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)03l2 tlb miss data (0b)1e3f4d51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
10204100357500829877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001001071013711994110000101001003610036100361003610036
102041003575006179877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001000071013711994110000101001003610036100361003610036
102041003575008359877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001001229571013711994110000101001003610036100361003610036
10204100357510619877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001000071013711994110000101001003610036100361003610036
10204100357500619877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001000071013711994110000101001003610036100361003610036
102041003575001959877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001000071013711994110000101001003610036100361003610036
10204100358100849877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001000071013711994110000101001003610036100361003610036
102041003575001249877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001004071013711994110000101001003610036100361003610036
102041003575006198772510100101001010088664496955100351003585803872210100102002020010035411110201100991001010010001271013721994110000101001003610036100361003610036
10204100357500619877251010010100101008866449695510035100358580387221010010200202001003541111020110099100101001000071013711994110000101001003610036100361003610036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

retire uop (01)cycle (02)033f4d5051schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d tlb miss (a1)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
100241003575103986310019251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000364024132994010000100101003610036100361003610036
100241003575145986310019251001010010100108878449695510035100358602387401001010020200201003541111002110910100101040064024132994010000100101003610036100361003610036
100241003576214986302510010100101001088784496955100351003586023874010010100202002010035411110021109101001010001264024122994010000100101003610036100361003610036
1002410035756198630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000064024122994010000100101003610036100361003610036
1002410035756198630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101001064024122994010000100101003610036100361003610036
1002410035756198630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000364024132994010000100101003610036100361003610036
10024100357578198630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000064024132994010000100101003610036100361003610036
10024100357512498630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000064024132994010000100101003610036100361003610036
1002410035756198630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000364024122994010000100101003610036100361003610036
1002410035756198630251001010010100108878449695510035100358602387401001010020200201003541111002110910100101000064024122994010000100101003610036100361003610036

Test 4: throughput

Count: 8

Code:

  asr x0, x8, x9
  asr x1, x8, x9
  asr x2, x8, x9
  asr x3, x8, x9
  asr x4, x8, x9
  asr x5, x8, x9
  asr x6, x8, x9
  asr x7, x8, x9
  mov x8, 9
  mov x9, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.1673

retire uop (01)cycle (02)031e3f51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)696a6d6emap stall dispatch (70)int prf full (71)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? int retires (ef)f5f6f7f8fd
80204134191010203258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100005111619551338380000801001338713387133871338713387
8020413386100035258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100235111519521338380000801001338713387133871338713387
80204133861000164258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100105111519631338380000801001338713387133871338713387
8020413386101035258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100005111419551338380000801001338713387133871338713387
8020413386100035258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100005111419651338380000801001338713387133871338713387
8020413386100035258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100005111419531338380000801001339213392133871338713387
8020413386100077258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100005111419431338380000801001338713387133871338713387
8020413386100077258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100135111419541338380000801001338713387133871338713387
80204133861010144258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100005111319331338380000801001338713387133871338713387
8020413386103035258010080100801004005004910306133861338633230333418010080200160200133863911802011009910080100100035111419551338380000801001338713387133871338713387

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.1671

retire uop (01)cycle (02)03l2 tlb miss data (0b)181e3f51schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)60696a6d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map int uop inputs (7f)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)9fl1d tlb access (a0)l1d cache writeback (a8)accfd5map dispatch bubble (d6)d9daddfetch restart (de)e0? int output thing (e9)ea? int retires (ef)f5f6f7f8fd
80024133861000307232580010800108001040005004910291133711337133303334880010800201600201337139118002110910800101000050201119806613368800000800101337213372133721337213372
8002413371100000415258001080010800104000501491029113371133713330333488001080020160020133713911800211091080010100005020219602213368800000800101337213433133721337213372
8002413371100000465258001080010800104000500491029113371133713330333488001080020160554133713911800211091080010100205020219602613368800000800101337213372133721337213372
800241337110000077258013780010800104000501491029113371133713330333488001080020160020134333911800211091080010100005020219802213368800000800101337213372133721337213372
800241337110000058258001080010800104000500491029113371133713330333488001080020160020133713911800211091080010100005022219602213368800000800101337213372133721337213372
800241337110000058258001080010800104000500491029113371133713330333488001080020160020133713911800211091080010100005020219406213368800000800101337213372133721337213372
8002413371100000190258001080010800104000500491029113371133713330333488001080020160020133713911800211091080010100005020219602213368800000800101337213372133721337213372
800241337110000079258001080010800104000500491029113371133713330333488001080020160020133713911800211091080010100005020219606213368800000800101337213372133721337213372
8002413371100000277258001080010800104000500491029113371133713330333488001080020160020133713911800211091080010100005020419602213368800000800101337213372133721337213372
8002413371100000100258001080010800104000500491029113371133713330333488001080020160020133713911800211091080010100005020219602213368800000800101337213372133721337213372