Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (scalar, fixed-point, D from D)

Test 1: uops

Code:

  ucvtf d0, d0, #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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723014825472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372408625472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723012425472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723012525472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf d0, d0, #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)030b191e3f4e51inst 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)9d9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071021611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000100071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130054300373003728264328745101002041000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038
102043003723300044129547251010010210000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038
10204300372320006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038
10204300372410006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000200071011611296330100001003003830038300383003830038
102043003723300025729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500024061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640416332962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640316322962910000103003830038300383003830038
10024300372250000089295472510010101000010100005042771600300183022330037282863287671001020100002010000300373003711100211091010100001000000640316332962910000103003830038300383003830038
10024300372240000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640316332962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640316332962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300653003730037282863287671001020100002010000300373003711100211091010100001000000640316232962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000003640316332962910000103003830038300383003830038
100243003722500027061295474210010111000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640316332963610000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640316332962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640316332962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf d0, d8, #3
  ucvtf d1, d8, #3
  ucvtf d2, d8, #3
  ucvtf d3, d8, #3
  ucvtf d4, d8, #3
  ucvtf d5, d8, #3
  ucvtf d6, d8, #3
  ucvtf d7, d8, #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)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)9fa1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039155005825801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155005825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000311151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)5f60696d6edispatch 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115501066258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020716652003680000102004020040200402004020040
8002420039155040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020816652003680000102004020040200402004020040
80024200391550325258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616662003680000102004020040200402004020040
8002420039156040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020716772003680000102004020040200402004020040
8002420039155040258001010800001080000506400000120020200392003999963100198001020800002080000200392009211800211091010800001000005020716652003680000102004020040200402004020040
8002420039156040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000105020516562003680000102004020040200402004020040
800242003915502749258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616752003680000102004020040200402004020040
8002420039155040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616452003680000102004020040200402004020040
8002420039155040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020616562003680000102004020040200402004020040
80024200391550402580010108000010800005064000001200202003920039100243100198001020800002080000200392003911800211091010800001000005020516572003680000102004020040200402004020040