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, integer, 4H from 4H)

Test 1: uops

Code:

  scvtf v0.4h, v0.4h
  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)0318191e3f4e51inst 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)a0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200121032547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230012612547251000100010003981601301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037230012612547251000100010003981600301830373037241432895100010001000303730371110011000001073116112629100030383038303830383038
10043037220012612547251000100010003981600301830373037241432895100010001000303730371110011000000373116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
10043037220012612547251000100010003981600301830373037241432895100010001000303730371110011000901073116112629100030383038303830383038
1004303722000612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
100430372300151032547251000100010003981600301830373037241432895100010001000303730371110011000001073116112629100030383038303830383038
10043037220001032547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf v0.4h, v0.4h
  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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225123103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000137101161129633100001003003830038300383003830038
1020430037225459103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000137101161129633100001003003830038300383003830038
1020430037225297103295472510100100100001001000050042771601300183003730037282648287451010020010000200100003003730037111020110099100100100001002037101161129633100001003003830038300383003830038
10204300372251144011295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000107101161129633100001003003830038300383003830038
1020430037225255103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722531261295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000137101161129633100001003003830038300383003830038
10204300372250103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722530061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000107101161129633100001003003830038300383003830038
1020430037225361295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225961295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064031622296290010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010163201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
1002430037225000085808429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
100243003722500000025129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064021622296290010000103003830038300383003830038
10024300372250000006129475170100891410072131135010342879761303063046330462283134328936113632411484221148530461304671011002110910101000010003002235832832310143299534010000103045630463304633049930480
10024304642280091013208806129547251003710100481811411764290603130378301793046128326192893611518281156724114953046330462101100211091010100001022211227833481027233299712010000103051230509303213046330514

Test 3: throughput

Count: 8

Code:

  scvtf v0.4h, v8.4h
  scvtf v1.4h, v8.4h
  scvtf v2.4h, v8.4h
  scvtf v3.4h, v8.4h
  scvtf v4.4h, v8.4h
  scvtf v5.4h, v8.4h
  scvtf v6.4h, v8.4h
  scvtf v7.4h, v8.4h
  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)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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001011151181160020036800001002004020040200402004020040
80204200391500030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000035011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000436611151180160020036800001002004020040200402004020040
802042003915000302580108100802081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000029011151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000033311151180160020036800001002004020040200402004020040
8020420039150006952580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000030311151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000040311151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000028311151180160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000044511151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3a3f51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150001200402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001005020416342003680000102004020040200402004020040
8002420039150001200402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000035020316532003680000102004020040200402004020040
8002420039150001200402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001035020516332003680000102004020040200402004020040
800242003915000000822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001035020416452003680000102004020040200402004020040
8002420039150001200822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001035020416332003680000102004020040200402004020040
8002420039150001200822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000035020316352003680000102004020040200402004020040
800242003915000000822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001005020416442003680000102004020040200402004020040
800242003915000000822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000035020416432003680000102004020040200402004020040
8002420039150001200822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001035020416342008680000102004020040200402004020040
8002420039150006007012580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001005020416422003680000102004020040200402004020040