Apple M1 Microarchitecture Research by Dougall Johnson

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

UXTL (2D)

Test 1: uops

Code:

  uxtl v0.2d, v0.2s
  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)03191e3f4e51inst 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)a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895100010001000203720371110011000010073116111786100020382038203820382038
10042037150061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895115210001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042085160061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
10042037160061168625100010001000264521201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uxtl v0.2d, v0.2s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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
1020420037155068919686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155066119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155066119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037156006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371560186119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037156066119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037155006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371550082819686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037156006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa0a8a9acmemory order violation (c4)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010040006403162219786010000102003820038200382003820038
10024200371550000611968625100101010000101000050284752102001820037200371844331876710010221000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371600000611968625100101010000101000050284752112001820037201331844331876710010201000020100002003720037111002110910101000010000006402482219786010000102003820038200382003820038
100242003715500007201968625100101010012101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371550000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000306402162219786010000102003820038200382003820038
10024200371560000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000306402162219786010000102003820038200382003820038
10024201781550000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371550000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010200006402162219786010000102003820038200382003820038
10024200371550000611968625100101010000101000050284752102016220037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371560000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uxtl v0.2d, v8.2s
  uxtl v1.2d, v8.2s
  uxtl v2.2d, v8.2s
  uxtl v3.2d, v8.2s
  uxtl v4.2d, v8.2s
  uxtl v5.2d, v8.2s
  uxtl v6.2d, v8.2s
  uxtl v7.2d, v8.2s
  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)0318191e1f3f51inst 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)9fa0a1a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057156000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
8020420038155000029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
8020420038155000029258010810080008100800205006401321200572003820038997706998980120200800322008003220038200381180201100991001008000010000100111511801600200350800001002003920039200392003920039
8020420038155000029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381550072029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
80204200381550012029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
802042003815500002925801081008000810080020500640132120019200382003899770699898012020080032200800322003820038118020110099100100800001000010011151180160020035250800001002003920039200392003920039
8020420038161000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
8020420038155000029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039
8020420038156000029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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
8002420050155003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502010169112003580000102003920039200392003920039
80024200381610039258001010800001080000506409200200192003820038999631001880010208000020800002003820038218002110910108000010005020121612102003580000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020111611122003580000102003920039200392003920039
80024200381560039258001010800001080000506400000200192003820038999631001880010208019520800002003820038118002110910108000010005020101610132003580000102003920039200392003920039
800242003815501839258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020121611102003580000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020111611112003580000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020101610112003580000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020131610122003580000102003920039200392003920039
80024200381600039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020111611102003580000102003920039200392003920039
80024200381550039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020111610132003580000102003920039200392003920039