Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (vector, zero, 2S)

Test 1: uops

Code:

  fcmge v0.2s, v0.2s, #0
  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)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
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
100420371504861168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
100420371504861168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038
100420371502161168625100010001000264521020182037203715713189510001000100020372037111001100073216111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge v0.2s, v0.2s, #0
  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)030b1e3a3f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500180611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100003071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000126071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100010071011611197910100001002003820038200382003820038
1020420037149000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372008411102011009910010010000100000071011611197912100001002003820038200382003820038
10204200371500004411968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100050071011611197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000570071011611197910100001002003820038200382003820038
10204200371500002321968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371505241968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371491241968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371501261968644100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371501661968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820085
10024200371501241968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371501491968625100101010000101000050284752112001820037200371844331876710010201000020100002003720084111002110910101000010006402162219786010000102003820038200382003820038
1002420037150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371501031968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371491451968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
10024200371501031968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmge v0.2s, v8.2s, #0
  fcmge v1.2s, v8.2s, #0
  fcmge v2.2s, v8.2s, #0
  fcmge v3.2s, v8.2s, #0
  fcmge v4.2s, v8.2s, #0
  fcmge v5.2s, v8.2s, #0
  fcmge v6.2s, v8.2s, #0
  fcmge v7.2s, v8.2s, #0
  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)030b1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184162320035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000311151183163320035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183162220035800001002003920039200392003920039
8020420038150002192580108100800081008011250064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183162220081800001002003920039200392003920039
802042003815000522580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184164420035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184163420035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183163320035800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182163220035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184163420153800001002003920039200392003920039
802042003815000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151184162220035800001002003920039200392003920039

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)6061696d6edispatch 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)9fa0cfd0d2d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005114906392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010050200011260332003580000102003920039200392003920039
80024200381500039258001010800001080000506407600020019200382003899963100188001020800002080000200382003811800211091010800001005020523160732003580000102003920039200392003920039
800242003815001539258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020523160742003580000102003920039200392003920039
8002420038150038439258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020523160372003580000102003920039200392003920039
800242003815002439258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001005020023160332003580000102003920039200392003920039
800242003815002439258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020503160732003580000102003920039200392003920039
80024200381500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001015020003160372003580000102003920039200392003920039
800242003815001839258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001005020003160772003580000102003920039200392003920039
800242003815003339258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001005020533160332003580000102003920039200392003920039
80024200381500039258001010800001080000506400001520019200382003899963100188001020800002080000200382003811800211091010800001005020003160332003580000102003920039200392003920039