Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (vector, 2D)

Test 1: uops

Code:

  shl v0.2d, v0.2d, #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)03081e3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100073324221786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100073216221786100020382038203820382038
1004203715010561168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100073216211786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl v0.2d, v0.2d, #3
  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)0308090b18191e1f3f4e51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100004037102161119791100001002003820038200382003820038
1020420037150000000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000050787101161119791100001002003820038200382003820038
102042003715100000006119686251018210010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100006007101161119897100001002003820038200382003820038
1020420037150000001206119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100008007101161119791100001002003820038200382003820038
102042003715000000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100005037101161119791100001002003820038200382003820038
102042003715000000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042013215000000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100008007101161119791100001002003820038200382003820038
102042017815000000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100009007101161119791100001002003820038200382003820038
102042003715000000006119686251010010010000109101525002847521020018200372003718421318745101002001000020010000200372003741102011009910010010000100004007101161119791100001002003820038200382003820038
10204200371500000000154419686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003741102011009910010010000100008007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e1f3f4e51inst 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
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001030640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001080640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001070640216221978610000102003820038200382003820038
1002420037151000611968625100101010000101000050284752102001820037200371844371876710010201000020100002003720037111002110910101000010490640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001013640216221978610000102003820038200382003820038
100242003714900061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003721100211091010100001031978640216221978610000102003820038200382003820038
100242003715100061196862510010101000010100007128487850200182003720037184433187671001020100002010000200372003711100211091010100001023640216221978610000102003820038200382003820038
10024200371510128861196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001016640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001013640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001026640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl v0.2d, v8.2d, #3
  shl v1.2d, v8.2d, #3
  shl v2.2d, v8.2d, #3
  shl v3.2d, v8.2d, #3
  shl v4.2d, v8.2d, #3
  shl v5.2d, v8.2d, #3
  shl v6.2d, v8.2d, #3
  shl v7.2d, v8.2d, #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)031e1f3a3f51inst 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)9fa0a8acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381500002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010003300111511816020035800001002003920039200392003920039
8020420038150000502580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000130111511816020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150900292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381502100292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500009282580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000100111511816020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000000083258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000010305020161613102003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020121612122003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000010005020131613142003580000102003920039200392003920039
800242003814900000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020141614142003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020121613132003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020131613142003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020141613132003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020141614142003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020131614112003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020121612122003580000102003920139200392003920039