Apple M1 Microarchitecture Research by Dougall Johnson

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

MOVI (vector, 4S, zero)

Test 1: uops

Code:

  movi v0.4s, #0

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 0.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

retire (01)cycle (02)0308191e3f5160696d6escheduler rewind (75)scheduler stall (76)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10041522000271500134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153
10041522000271500134152152310152152111001100000740115111491000153153153153153
10041521000271501134152152310152152111001100000740115111491000153153153153153
10041521000271500134152152310152152111001100000740115111491000153153153153153

Test 2: throughput

Count: 8

Code:

  movi v0.4s, #0
  movi v1.4s, #0
  movi v2.4s, #0
  movi v3.4s, #0
  movi v4.4s, #0
  movi v5.4s, #0
  movi v6.4s, #0
  movi v7.4s, #0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.1258

retire (01)cycle (02)03181e3f51inst issue (52)~issue int (53)~dispatch int (56)huge thing int (59)60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map lookup int (7f)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
8020410076780035955410010010050001003410060100603181002002001006010060118020110099100100800001000051156165510057800001001006110061100611006110061
8020410060780035955410010010050001003410060100603181002002001006010060118020110099100100800001001051155163510057800001001006110061100611006110061
8020410060770035955410010010050001003410060100603181002002001006010060118020110099100100800001000051155165510057800001001006110061100611006110061
8020410060780035955410010010050001003410060100603181002002001006010060118020110099100100800001000051154165510057800001001006110061100611006110061
80204100607800359554100100100500010034100601006031810020020010060100601180201100991001008000010029051133163510057800001001006110061100611006110065
80204100607800676955410010010050001003410060100603181002002001006010060118020110099100100800001000051163165510057800001001006110061100611006110061
80204100607800359554100100100500010034100601006031810020020010060100601180201100991001008000010026051166165510057800001001006110061100611006110061
8020410060780035955410010010050011003410060100603181002002001006010060118020110099100100800001000051133164510057800001001006110061100611006110061
8020410060780035955410010010050001003410060100603181002002001006010060118020110099100100800001000051146164610057800001001006110061100611006110061
8020410060780035955410010010050001003410060100603181002002001006010060118020110099100100800001000351165164610057800001001006110061100611006110061

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.1255

retire (01)cycle (02)03070a18191e3f51inst issue (52)~issue int (53)~dispatch int (56)huge thing int (59)5f60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map lookup int (7f)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)9fa8accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002410053780012077998210101050001001210038100383181020201003810038118002110910108000010035034171608171003580000101003910039100391003910039
80024100387800000359982101010500010012100381003831810202010038100381180021109101080000102650361016017151003580000101003910039100391003910039
800241003878000003599821010105000100121003810038318102020100381003811800211091010800001001250361616014161003580000101003910039100391003910039
800241003878000003599821010105001100121003810038318102020100381003811800211091010800001001250341416017131003580000101003910039100391003910039
800241003878000003599821010105001100121003810038318102020100381003811800211091010800001002150361616013161003580000101003910039100391003910039
80024100387720000359982101010560110012100381003831810202010038100381180021109101080000100050321616016171003580000101003910039100391003910118
8002410038781000035998210121050011001210038100383181020201003810038118002110910108000010065029916017141003580000101003910039100391003910104
800241003878010003599821012105000100121003810038318102020100381003811800211091010800001009050341416017141003580000101003910039100391003910104
800241003878000003599821012105001100121003810038318102020100381003811800211091010800001020050361616016161003580000101003910039100391003910104
800241003877000003599821012105001100121003810038318102020100381003811800211091010800001070503091601781003580000101003910039100391003910120