Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHRUN (8H)

Test 1: uops

Code:

  sqshrun v0.8b, v0.8h, #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)031e3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372396125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030743085303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000301273216222629100030383038303830383038
100430372396125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372336125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372236125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000373216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000013073216222629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrun v0.8b, v0.8h, #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)03181e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101001001000010010000500427716030018300373003728264328745101002001000020010331300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372250012332954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100001710011611296330100001003003830038300383003830038
1020430037225017710772954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372250010152954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372250012372954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372250010022954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372240912832954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372250012342954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372250010612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372240012322954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa0a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201018030037300371110021109101010000100002006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100003006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100001006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100001006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100001006402162229629010000103003830038300383003830038
100243003722400612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100001006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100002306402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100001006402162229629010000103003830084300383003830038
100243003722500612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100001006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrun v0.8b, v8.8h, #3
  sqshrun v1.8b, v8.8h, #3
  sqshrun v2.8b, v8.8h, #3
  sqshrun v3.8b, v8.8h, #3
  sqshrun v4.8b, v8.8h, #3
  sqshrun v5.8b, v8.8h, #3
  sqshrun v6.8b, v8.8h, #3
  sqshrun v7.8b, v8.8h, #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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500076025801081008000810080020500640132020020200392009299770699908012020080032200800322003920039218020110099100100800001000011151182162120036800001002004020040200402004020040
80204200391500135725801081008000810080126500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161220036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997706999080120200800322008003220039200391180201100991001008000010044011151182162120036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132020138200392019999770699908012020080032200800322003920039118020110099100100800001000011151181161220036800001002004020040200402004020040
8020420039150005325801081008000810080020500640132020083200392003999770699908012020080032200800322003920039118020110099100100800001000011151182161220036800001002004020040200402004020040
80204200391500041525801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000011151182162220036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161220036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000011151182161220036800001002004020040200402004020040
80204200391500030425801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000011151182162120036800001002004020142200402004020040
80204200391500022025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000011151182162220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0309191e3a3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000122254258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020516662003680000102004020040200402004020040
8002420039150006127425801071080000108021350640000020020200392009799963010019800102080000208000020039201901180021109101080000101019005020616762003680000102004020040200402004020040
8002420039150000182258001010800001080000506400000200202003920039999631001980010208000020800002024320039118002110910108000010105020816772003680000102004020040200402004020040
80024200391500002103258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010105020716652003680000102004020040200402004020040
800242003915000121347258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010035020816782003680000102004020040200402004020040
8002420039150000182258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020616572003680000102004020040200402004020040
80024200391500001269258020310800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010105020516562003680000102004020040200402004020040
80024200391500001213258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020516582003680000102004020040200402004020040
8002420039150000140258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010035020616772003680000102004020040200402004020040
8002420039150000140258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020816652003680000102004020040200402004020040