Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (vector, fixed-point, 2S from 2S)

Test 1: uops

Code:

  scvtf v0.2s, v0.2s, #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)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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100010073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000673116112629100030383038303830863038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383061303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037231261254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303722082254725100010001000398160030183037303724143289510001000100030373037111001100010073116112629100030383038303830383038
1004303723098254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230612547251000100010003981600301830373037241432895100010001000303730371110011000150373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf v0.2s, v0.2s, #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)03080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000012001032954725101001001000010010000500427851213001830037300372826432874510100200100002001000030037300371110201100991001001000010000010308510367222984722100001003037030134303713037230326
102043022822700176825528244152948415610194111100481381105067842865471300903037130372282883228875111932241116122611161303703040381102011009910010010000100422141966327550473222992133100001003041930182304253037030421
1020430470227000881203704152602947411610209150100721521120073342879391303063040730468282893328873113432321116122411333304693041891102011009910010010000100400002489007631182312996926100001003047030466304183046530465
102043041622811189106570425260295111751021014710072142110507574287976130342304163042428297412889311389210111602321132330413304181011020110099100100100001000200225108274203106132995737100001003045330466304233041830171
102043045122810183120070415340294661921022114710064147112006644287976130306304683046528302392891311342229111642321131530416304639110201100991001001000010024220252330710011611296330100001003003830038300383003830038
10204300372250000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000001000710011611296330100001003003830038300383003830038
102043003722500000000103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000030710011611296330100001003003830038300383003830038
1020430037225000001200103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000001030710011611296330100001003003830038300383003830038
102043003722500000000103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000030710011611296330100001003003830038300383003830038
1020430037225000001200103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000030710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000306402162229667010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000060006402162229629010000103003830038300383003830038
100243003722500010061295472510010111000010100005042771603001830037300372828632876710161201000020100003003730037111002110910101000010000010006402162229629210000103003830038301323027530275
100243032422800678045283966294841501008112100481711200714285272302703036930368283093828914111602610985201114630132303708110021109101010000100031141962847042733229881210000103041430366303583041830368
1002430417227109411887046129547251001010100001010000504277160300183003730037282862228822104622010000211098230308301782110021109101010000102200042226628302883330068310000103051330558305123051130555
100243041722811101013058806576294572361010118100801410450109429068030378305613041528323328767100102010000201000030037300371110021109101010000102020101983508292813229978310000103051230466301313051330419
1002430495228101071323880657929457190101071410080231135061428932830342305083046428314152893611216241049322106583003730037111002110910101000010020004849026403562229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf v0.2s, v8.2s, #3
  scvtf v1.2s, v8.2s, #3
  scvtf v2.2s, v8.2s, #3
  scvtf v3.2s, v8.2s, #3
  scvtf v4.2s, v8.2s, #3
  scvtf v5.2s, v8.2s, #3
  scvtf v6.2s, v8.2s, #3
  scvtf v7.2s, v8.2s, #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)031e1f3f51inst 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)60696b6d6edispatch 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500072258010810080008100800205006401320200200200392003999776999080120200800322008014320093200391180201100991001008000010011211151182162220036800001002004020040200402004020040
80204200391501207225801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001311151181162120036800001002004020040200402004020040
80204200391501207225801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001311151363161220036800001002004020040200402004020040
802042003915012039163801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001311151182162020036800001002004020040200402004020040
8020420039150007225801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001001311151181163220036800001002004020040200402004020040
80204200391501203025801081008000810080020500640132120020020039200399977699908012020080032200800322009020039118020110099100100800001000011151182162120036800001002004020040200402004020040
80204200391501207225801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000311151182162220036800001002004020040200402004020040
80204200391500011425801081008000810080020500640132020020320039200399977699908012020080032200800322003920039118020110099100100800001000311151181161220036800001002004020040200402004020040
80204200391501203025801081008000810080020500640132020020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181161220036800001002004020040200402004020040
80204200391501203025801081008000810080020500640132120020020039200399977699908012020080032200800322003920039118020110099100100800001001311151182161220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050206167172003680000102004020040200402004020040
800242003915000230258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000502017161772003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050208161782003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000502017166172003680000102004020040200402004020040
800242003915000696258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010200502017168172003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000502017166172003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020171617172003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000502017161462003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050206161782003680000102004020040200402004020040
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050208161762003680000102004020040200402004020040