Apple M1 Microarchitecture Research by Dougall Johnson

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

SQNEG (vector, 4S)

Test 1: uops

Code:

  sqneg v0.4s, v0.4s
  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)030b181e3f4e51inst 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
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037221006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723002161254743100010001000398160030183037303724143289510001000100030373037111001100002473116112629100030383038303830383038
10043037220006125472510001000100039816013018303730372414328951000100010003037303711100110003073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037220006125472510001000100039816003018303730372414328951000100010003037303711100110004073116112629100030383038303830383038
10043037220006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372200061254725100010001000398160130183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg v0.4s, v0.4s
  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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007102161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730084282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000027101161129633100001003003830038301803003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03193f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329701010000103003830038300383003830038
1002430037225061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037224061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010206403163329629010000103003830038300383003830038
1002430037225161295362510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037224061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037224061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqneg v0.4s, v8.4s
  sqneg v1.4s, v8.4s
  sqneg v2.4s, v8.4s
  sqneg v3.4s, v8.4s
  sqneg v4.4s, v8.4s
  sqneg v5.4s, v8.4s
  sqneg v6.4s, v8.4s
  sqneg v7.4s, v8.4s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030708090a1e3f51inst 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
8020420059150100103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151185161120036800001002004020040200402004020040
8020420039150100103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150100107225801081008000810080020500640132120020200392003999776999080120200801422008013820039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150100109325801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001011151181161120036800001002004020040200402004020040
8020420039150100103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200942004020040
8020420039150100103025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001011151181161120036800001002004020040200402004020040
80204200391501001011425801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150100105125801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150100103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150100103025801081008000810080020500640132120020200392003999776999080120200800382008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b191e1f3f51inst 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)6061696b6d6edispatch 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)9fa0a8accfd0d2d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420201151000214117640258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100205020003160112003680000102004020040201422004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100005020001160112003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100005020001160112003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100005020001160112003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100105020001160112003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100105020001160112003680000102004020245200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019801152080000208000020039200391180021109101080000100005020001164222003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100005020001160112003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100005020002160212003680000102004020040200402004020040
800242003915000000040258001010800001080000506400001020020020039200399996310019800102080000208000020039200391180021109101080000100005020001160112003680000102004020040200402004020040