iwia021h@testfront1:~/MD-Bench/asm$ /home/hpc/iwia/iwia021h/.local/bin/osaca --ignore-unknown --arch=CSX force_soa_lt8_markers.s Open Source Architecture Code Analyzer (OSACA) - 0.3.14 Analyzed file: force_soa_lt8_markers.s Architecture: CSX Timestamp: 2021-04-29 15:52:48 P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction * - Instruction micro-ops not bound to a port X - No throughput/latency information for this instruction in data file Combined Analysis Report ------------------------ Port pressure in cycles | 0 - 0DV | 1 | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 || CP | LCD | ------------------------------------------------------------------------------------------------- 300 | | | | | | | | || | | # LOE rax rdx rbp rsi rdi r8 r10 r11 r12 ebx r13d xmm8 xmm9 xmm10 ymm17 ymm18 zmm7 zmm11 zmm12 zmm13 zmm14 zmm15 zmm16 zmm19 301 | | | | | | | | || | | ..B1.25: # Preds ..B1.24 302 | | | | | | | | || | | # Execution count [2.50e+01] 303 | | 1.00 | | | | | | || 3.0 | | imulq %r12, %r8 #56.43 304 | | | | | | 1.00 | | || | | vbroadcastsd %xmm9, %zmm9 #59.23 305 | | | | | | 1.00 | | || | 3.0 | vbroadcastsd %xmm8, %zmm2 #58.23 306 | | | | | | 1.00 | | || | | vbroadcastsd %xmm10, %zmm10 #60.23 307 | | | | | | | | || | | X subl %ebx, %r13d #67.9 308 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || 1.0 | | addq %r11, %r8 #37.5 309 | | | | | | | | || | | X vpbroadcastd %r13d, %ymm0 #67.9 310 | | | | | | 1.00 | | || | | vpcmpgtd %ymm17, %ymm0, %k5 #67.9 311 | 0.00 | 0.16 | | | | 0.00 | 0.84 | || | | movslq %ebx, %rbx #67.9 312 | | | | | | | | || | | * vmovaps %zmm19, %zmm4 #70.36 313 | 1.00 | | | | | | | || | | kmovw %k5, %k2 #70.36 314 | | | | | | | | || | | * vmovaps %zmm19, %zmm3 #69.36 315 | 0.00 | 1.00 | 0.50 0.50 | 0.50 0.50 | | 0.00 | | || 0.0 | | vmovdqu32 (%r8,%rbx,4), %ymm1{%k5}{z} #68.21 316 | 1.00 | | | | | | | || | | kmovw %k5, %k1 #69.36 317 | | | | | | | | || | | * vmovaps %zmm19, %zmm5 #71.36 318 | 1.00 | | | | | | | || | | kmovw %k5, %k3 #71.36 319 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rsi,%ymm1,8), %zmm5{%k3} #71.36 320 | 1.50 | 0.34 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.66 | || 4.0 | | vgatherdpd (%rax,%ymm1,8), %zmm4{%k2} #70.36 321 | 1.50 | 0.00 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 1.00 | || | | vgatherdpd (%rdx,%ymm1,8), %zmm3{%k1} #69.36 322 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm5, %zmm10, %zmm30 #71.36 323 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm4, %zmm9, %zmm28 #70.36 324 | 0.50 | | | | | 0.50 | | || | 4.0 | vsubpd %zmm3, %zmm2, %zmm27 #69.36 325 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm28, %zmm28, %zmm26 #72.49 326 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd231pd %zmm27, %zmm27, %zmm26 #72.49 327 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd231pd %zmm30, %zmm30, %zmm26 #72.63 328 | 2.50 | | | | | 0.50 | | || 8.0 | 8.0 | vrcp14pd %zmm26, %zmm25 #75.38 329 | | | | | | 1.00 | | || | | vcmppd $1, %zmm16, %zmm26, %k6{%k5} #74.22 330 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm25, %k0 #75.38 331 | | | | | | | | || | | * vmovaps %zmm26, %zmm6 #75.38 332 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | 4.0 | vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm25, %zmm6 #75.38 333 | 1.00 | | | | | | | || | | knotw %k0, %k4 #75.38 334 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vmulpd %zmm6, %zmm6, %zmm8 #75.38 335 | 0.50 | | | | | 0.50 | | || | | vfmadd213pd %zmm25, %zmm6, %zmm25{%k4} #75.38 336 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd213pd %zmm25, %zmm8, %zmm25{%k4} #75.38 337 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm15, %zmm25, %zmm20 #76.38 338 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm14, %zmm25, %zmm22 #77.54 339 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm20, %zmm25, %zmm23 #76.44 340 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm23, %zmm25, %zmm21 #76.50 341 | 0.50 | | | | | 0.50 | | || | | vfmsub213pd %zmm7, %zmm23, %zmm25 #77.54 342 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm22, %zmm21, %zmm24 #77.61 343 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm25, %zmm24, %zmm29 #77.67 344 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm27, %zmm29, %zmm13{%k6} #78.17 345 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm28, %zmm29, %zmm12{%k6} #79.17 346 | 0.00 | | | | | 1.00 | | || 4.0 | | vfmadd231pd %zmm30, %zmm29, %zmm11{%k6} #80.17 19.5 3.50 13.0 2.50 13.0 2.50 19.5 3.50 68.0 31.0 Loop-Carried Dependencies Analysis Report ----------------------------------------- 308 | 4.0 | addq %r11, %r8 #37.5| [303, 308] 304 | 3.0 | vbroadcastsd %xmm9, %zmm9 #59.23| [304] 306 | 3.0 | vbroadcastsd %xmm10, %zmm10 #60.23| [306] 307 | 0.0 | subl %ebx, %r13d #67.9| [307] 311 | 1.0 | movslq %ebx, %rbx #67.9| [311] 346 | 4.0 | vfmadd231pd %zmm30, %zmm29, %zmm11{%k6} #80.17| [346] 345 | 4.0 | vfmadd231pd %zmm28, %zmm29, %zmm12{%k6} #79.17| [345] 344 | 4.0 | vfmadd231pd %zmm27, %zmm29, %zmm13{%k6} #78.17| [344] 334 | 31.0 | vmulpd %zmm6, %zmm6, %zmm8 #75.38| [305, 324, 326, 327, 328, 332, 334]