Apple M1 Microarchitecture Research by Dougall Johnson

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

RSHRN (2D)

Test 1: uops

Code:

  rshrn v0.2s, v0.2d, #3
  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)03093f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372201052547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  rshrn v0.2s, v0.2d, #3
  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)9fa0a1a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225135612954725101001001000010010000500427716003002230037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
102043003722545612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011622296330100001003003830038300383003830038
10204300372250612954725101001001000710010000500427716003001830037300372826432874510100200100002001000030037300841110201100991001001000010000000071031622296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200101752001000030037300371110201100991001001000010000000171021622296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716003001830131300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e1f3f4e51inst 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)696d6edispatch 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000270612954725100101010000101000050427716030018300373017728286328767100102010000201000030037300371110021109101010000100640224222962910000103003830038300383003830038
100243003722500000662954725100101010000101000050427716030018300373007628286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000822954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018302283003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  rshrn v0.2s, v8.2d, #3
  rshrn v1.2s, v8.2d, #3
  rshrn v2.2s, v8.2d, #3
  rshrn v3.2s, v8.2d, #3
  rshrn v4.2s, v8.2d, #3
  rshrn v5.2s, v8.2d, #3
  rshrn v6.2s, v8.2d, #3
  rshrn v7.2s, v8.2d, #3
  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)03191e1f3f51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150015030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100220011151180160020036800001002004020040200402004020040
8020420094150021030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915009030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100201011151180160020036800001002004020040200402004020040
8020420039150036030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090b1e1f3f51inst 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)9fa0a1a8a9accfd0d2d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420104150007504025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502000121605122003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980326208000020800002003920039118002110910108000010000005020008160562003680000102004020040200402004020040
800242003915000600402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100010050200051605112003680000102004020040200402009020040
80024200391500057040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020005160542003680000102004020040200402004020040
800242003915000150402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200011160542003680000102004020040200402004020040
80024200391500018040788001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020004160642003680000102004020040200402004020040
8002420039150001710822580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200051604102003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000050200051601052003680000102004020040201022004020040
80024200391500057040258001010800001080000506400001200592003920039999631001980010208000020800002003920039118002110910108000010000005020006160542003680000102004020040200402004020040
8002420039150000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020004160342003680000102004020040200402004020040