Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45 Analyzed File - lammps-icc-avx512.o Binary Format - 64Bit Architecture - SKX Analysis Type - Throughput Throughput Analysis Report -------------------------- Block Throughput: 30.89 Cycles Throughput Bottleneck: Backend Loop Count: 22 Port Binding In Cycles Per Iteration: -------------------------------------------------------------------------------------------------- | Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 | -------------------------------------------------------------------------------------------------- | Cycles | 19.0 0.0 | 4.0 | 13.0 13.0 | 13.0 13.0 | 0.0 | 17.0 | 4.0 | 0.0 | -------------------------------------------------------------------------------------------------- DV - Divider pipe (on port 0) D - Data fetch pipe (on ports 2 and 3) F - Macro Fusion with the previous instruction occurred * - instruction micro-ops not bound to a port ^ - Micro Fusion occurred # - ESP Tracking sync uop was issued @ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected X - instruction not supported, was not accounted in Analysis | Num Of | Ports pressure in cycles | | | Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 | ----------------------------------------------------------------------------------------- | 1 | | | | | | 1.0 | | | vpcmpgtd k5, ymm3, ymm4 | 1 | | 1.0 | | | | | | | vpaddd ymm4, ymm4, ymm15 | 2 | | 1.0 | 1.0 1.0 | | | | | | vmovdqu32 ymm17{k5}{z}, ymmword ptr [r10+r15*4] | 1 | | 1.0 | | | | | | | vpaddd ymm18, ymm17, ymm17 | 1 | | | | | | | 1.0 | | add r15, 0x8 | 1 | | 1.0 | | | | | | | vpaddd ymm19, ymm17, ymm18 | 1 | 1.0 | | | | | | | | kmovw k2, k5 | 1 | 1.0 | | | | | | | | kmovw k3, k5 | 1 | 1.0 | | | | | | | | kmovw k1, k5 | 1* | | | | | | | | | vpxord zmm21, zmm21, zmm21 | 1* | | | | | | | | | vpxord zmm20, zmm20, zmm20 | 1* | | | | | | | | | vpxord zmm22, zmm22, zmm22 | 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm21, k2, zmmword ptr [rbx+ymm19*8+0x8] | 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm20, k3, zmmword ptr [rbx+ymm19*8] | 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm22, k1, zmmword ptr [rbx+ymm19*8+0x10] | 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm18, zmm1, zmm21 | 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm17, zmm2, zmm20 | 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm19, zmm0, zmm22 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm31, zmm18, zmm18 | 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm31, zmm17, zmm17 | 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm31, zmm19, zmm19 | 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm30, zmm31 | 1 | | | | | | 1.0 | | | vcmppd k6{k5}, zmm31, zmm14, 0x1 | 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm30, 0x1e | 1* | | | | | | | | | vmovaps zmm23, zmm31 | 2^ | 1.0 | | | 1.0 1.0 | | | | | vfnmadd213pd zmm23, zmm30, qword ptr [rip]{1to8} | 1 | 1.0 | | | | | | | | knotw k4, k0 | 1 | | | | | | 1.0 | | | vmulpd zmm24, zmm23, zmm23 | 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm30{k4}, zmm23, zmm30 | 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm30{k4}, zmm24, zmm30 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm25, zmm30, zmm13 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm27, zmm30, zmm12 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm28, zmm30, zmm25 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm26, zmm30, zmm28 | 1 | 0.5 | | | | | 0.5 | | | vfmsub213pd zmm30, zmm28, zmm5 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm29, zmm26, zmm27 | 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm23, zmm29, zmm30 | 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm10{k6}, zmm23, zmm17 | 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm9{k6}, zmm23, zmm18 | 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm8{k6}, zmm23, zmm19 | 1* | | | | | | | | | cmp r15, r14 | 0*F | | | | | | | | | jb 0xffffffffffffff0c Total Num Of Uops: 57 Analysis Notes: Backend allocation was stalled due to unavailable allocation resources. There were bubbles in the frontend.