162 lines
19 KiB
Plaintext
162 lines
19 KiB
Plaintext
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
|
Analyzed file: gromacs-icx-avx512-sp.s
|
|
Architecture: CSX
|
|
Timestamp: 2023-02-10 16:31:04
|
|
|
|
|
|
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 |
|
|
--------------------------------------------------------------------------------------------------
|
|
1662 | | | | | | | | || | | # pointer_increment=64 0f91ac4f7fe1a70d0c899f7f3e745649
|
|
1663 | | | | | | | | || | | # LLVM-MCA-BEGIN
|
|
1664 | | | | | | | | || | | .LBB4_8: # =>This Inner Loop Header: Depth=1
|
|
1665 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | movslq (%r11,%rdx,4), %rax
|
|
1666 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || 1.0 | | movq %rax, %rsi
|
|
1667 | 0.00 | | | | | | 1.00 | || 1.0 | | shlq $5, %rsi
|
|
1668 | | 1.00 | | | | 0.00 | | || 1.0 | | leaq (%rsi,%rsi,2), %rbx
|
|
1669 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%rdi,%rbx), %zmm15 # AlignMOV convert to UnAlignMOV
|
|
1670 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 32(%rdi,%rbx), %zmm16 # AlignMOV convert to UnAlignMOV
|
|
1671 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmovups 64(%rdi,%rbx), %zmm27 # AlignMOV convert to UnAlignMOV
|
|
1672 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 128(%rsp), %zmm1 # 64-byte Reload
|
|
1673 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm24
|
|
1674 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 320(%rsp), %zmm1 # 64-byte Reload
|
|
1675 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm1, %zmm25
|
|
1676 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubps %zmm27, %zmm9, %zmm26
|
|
1677 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%rsp), %zmm1 # 64-byte Reload
|
|
1678 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm21
|
|
1679 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 256(%rsp), %zmm1 # 64-byte Reload
|
|
1680 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm1, %zmm22
|
|
1681 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm27, %zmm10, %zmm23
|
|
1682 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 448(%rsp), %zmm1 # 64-byte Reload
|
|
1683 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm17
|
|
1684 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 192(%rsp), %zmm1 # 64-byte Reload
|
|
1685 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm1, %zmm19
|
|
1686 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm27, %zmm11, %zmm20
|
|
1687 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 384(%rsp), %zmm1 # 64-byte Reload
|
|
1688 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm18
|
|
1689 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm8, %zmm16
|
|
1690 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm27, %zmm12, %zmm15
|
|
1691 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm26, %zmm26, %zmm27
|
|
1692 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231ps %zmm25, %zmm25, %zmm27 # zmm27 = (zmm25 * zmm25) + zmm27
|
|
1693 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231ps %zmm24, %zmm24, %zmm27 # zmm27 = (zmm24 * zmm24) + zmm27
|
|
1694 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm23, %zmm23, %zmm28
|
|
1695 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm22, %zmm22, %zmm28 # zmm28 = (zmm22 * zmm22) + zmm28
|
|
1696 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm21, %zmm21, %zmm28 # zmm28 = (zmm21 * zmm21) + zmm28
|
|
1697 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm20, %zmm20, %zmm29
|
|
1698 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm19, %zmm19, %zmm29 # zmm29 = (zmm19 * zmm19) + zmm29
|
|
1699 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm17, %zmm17, %zmm29 # zmm29 = (zmm17 * zmm17) + zmm29
|
|
1700 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm15, %zmm15, %zmm30
|
|
1701 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm16, %zmm16, %zmm30 # zmm30 = (zmm16 * zmm16) + zmm30
|
|
1702 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14ps %zmm27, %zmm31
|
|
1703 | 2.50 | | | | | 0.50 | | || | | vrcp14ps %zmm28, %zmm1
|
|
1704 | 2.50 | | | | | 0.50 | | || | | vrcp14ps %zmm29, %zmm2
|
|
1705 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm18, %zmm18, %zmm30 # zmm30 = (zmm18 * zmm18) + zmm30
|
|
1706 | 2.50 | | | | | 0.50 | | || | | vrcp14ps %zmm30, %zmm3
|
|
1707 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm31, %zmm6, %zmm4
|
|
1708 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm4, %zmm31, %zmm4
|
|
1709 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm4, %zmm31, %zmm4
|
|
1710 | 0.50 | | | | | 0.50 | | || 4.0 | | vaddps %zmm13, %zmm4, %zmm5
|
|
1711 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm7, %zmm31
|
|
1712 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm5, %zmm31, %zmm5
|
|
1713 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm6, %zmm31
|
|
1714 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm1, %zmm31
|
|
1715 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm1, %zmm31
|
|
1716 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm5, %zmm4, %zmm4
|
|
1717 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm13, %zmm31, %zmm5
|
|
1718 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm7, %zmm1
|
|
1719 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm5, %zmm1, %zmm1
|
|
1720 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm6, %zmm5
|
|
1721 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm5, %zmm2, %zmm5
|
|
1722 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm5, %zmm2, %zmm5
|
|
1723 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm31, %zmm1
|
|
1724 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm13, %zmm5, %zmm31
|
|
1725 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm7, %zmm2
|
|
1726 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm2, %zmm2
|
|
1727 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm3, %zmm6, %zmm31
|
|
1728 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm3, %zmm31
|
|
1729 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm3, %zmm31
|
|
1730 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm5, %zmm2
|
|
1731 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm13, %zmm31, %zmm5
|
|
1732 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm3, %zmm7, %zmm3
|
|
1733 | 1.00 | | | | | 0.00 | | || | | vmulps %zmm5, %zmm3, %zmm3
|
|
1734 | 1.00 | | | | | 0.00 | | || | | vmulps %zmm3, %zmm31, %zmm3
|
|
1735 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | xorl %esi, %esi
|
|
1736 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | xorl %edi, %edi
|
|
1737 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | testl $2147483647, %eax # imm = 0x7FFFFFFF
|
|
1738 | 0.00 | | | | | | 1.00 | || | | sete %sil
|
|
1739 | 0.00 | | | | | | 1.00 | || | | setne %dil
|
|
1740 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | movl $255, %eax
|
|
1741 | 0.00 | | | | | | 1.00 | || | | cmovel %r8d, %eax
|
|
1742 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | movl $255, %ecx
|
|
1743 | 0.00 | | | | | | 1.00 | || | | cmovel %r9d, %ecx
|
|
1744 | 0.00 | 0.25 | | | | 0.00 | 0.75 | || | | xorl $255, %esi
|
|
1745 | 1.00 | | | | | | | || | | kmovd %esi, %k1
|
|
1746 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm27, %k1 {%k1}
|
|
1747 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm14, %zmm4, %zmm4
|
|
1748 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm4, %zmm24, %zmm5 {%k1} {z}
|
|
1749 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm4, %zmm25, %zmm24 {%k1} {z}
|
|
1750 | 0.25 | | | | | 0.75 | | || | | vmulps %zmm4, %zmm26, %zmm4 {%k1} {z}
|
|
1751 | | 1.00 | | | | 0.00 | | || | | leal (%rdi,%rdi,2), %esi
|
|
1752 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | orl $252, %esi
|
|
1753 | 1.00 | | | | | | | || | | kmovd %esi, %k1
|
|
1754 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm28, %k1 {%k1}
|
|
1755 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm14, %zmm1, %zmm1
|
|
1756 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm21, %zmm21 {%k1} {z}
|
|
1757 | 0.50 | | | | | 0.50 | | || 4.0 | | vaddps %zmm21, %zmm5, %zmm5
|
|
1758 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm22, %zmm21 {%k1} {z}
|
|
1759 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm21, %zmm24, %zmm21
|
|
1760 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm23, %zmm1 {%k1} {z}
|
|
1761 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm1, %zmm4, %zmm1
|
|
1762 | 1.00 | | | | | | | || | | kmovd %eax, %k1
|
|
1763 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm29, %k1 {%k1}
|
|
1764 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm14, %zmm2, %zmm2
|
|
1765 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm17, %zmm4 {%k1} {z}
|
|
1766 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm19, %zmm17 {%k1} {z}
|
|
1767 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm20, %zmm2 {%k1} {z}
|
|
1768 | 1.00 | | | | | | | || | | kmovd %ecx, %k1
|
|
1769 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm30, %k1 {%k1}
|
|
1770 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm14, %zmm3, %zmm3
|
|
1771 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm3, %zmm18, %zmm18 {%k1} {z}
|
|
1772 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm18, %zmm4, %zmm4
|
|
1773 | 0.25 | | | | | 0.75 | | || 4.0 | | vaddps %zmm4, %zmm5, %zmm4
|
|
1774 | 0.00 | | | | | 1.00 | | || | | vmulps %zmm3, %zmm16, %zmm5 {%k1} {z}
|
|
1775 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm5, %zmm17, %zmm5
|
|
1776 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm5, %zmm21, %zmm5
|
|
1777 | 0.00 | | | | | 1.00 | | || | | vmulps %zmm3, %zmm15, %zmm3 {%k1} {z}
|
|
1778 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | movq 176(%r15), %rax
|
|
1779 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm3, %zmm2, %zmm2
|
|
1780 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%rax,%rbx), %zmm3 # AlignMOV convert to UnAlignMOV
|
|
1781 | 0.00 | | | | | 1.00 | | || 4.0 | | vsubps %zmm4, %zmm3, %zmm3
|
|
1782 | | | 0.50 | 0.50 | 1.00 | | | || 0.0 | | vmovups %zmm3, (%rax,%rbx) # AlignMOV convert to UnAlignMOV
|
|
1783 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm2, %zmm1, %zmm1
|
|
1784 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 32(%rax,%rbx), %zmm2 # AlignMOV convert to UnAlignMOV
|
|
1785 | 0.00 | | | | | 1.00 | | || | | vsubps %zmm5, %zmm2, %zmm2
|
|
1786 | | | 0.50 | 0.50 | 1.00 | | | || | | vmovups %zmm2, 32(%rax,%rbx) # AlignMOV convert to UnAlignMOV
|
|
1787 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 64(%rax,%rbx), %zmm2 # AlignMOV convert to UnAlignMOV
|
|
1788 | 0.00 | | | | | 1.00 | | || | | vsubps %zmm1, %zmm2, %zmm1
|
|
1789 | | | 0.50 | 0.50 | 1.00 | | | || | | vmovups %zmm1, 64(%rax,%rbx) # AlignMOV convert to UnAlignMOV
|
|
1790 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | cmpq %rdx, %r10
|
|
1791 | | | | | | | | || | | * je .LBB4_18
|
|
1792 | | | | | | | | || | | # %bb.9: # in Loop: Header=BB4_8 Depth=1
|
|
1793 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | movq 160(%r15), %rdi
|
|
1794 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | 1.0 | incq %rdx
|
|
1795 | 0.00 | | | | | | 1.00 | || | | jmp .LBB4_8
|
|
1796 | | | | | | | | || | | # LLVM-MCA-END
|
|
|
|
50.0 9.00 9.50 8.00 9.50 8.00 3.00 50.0 9.00 79.0 1.0
|
|
|
|
|
|
|
|
|
|
Loop-Carried Dependencies Analysis Report
|
|
-----------------------------------------
|
|
1794 | 1.0 | incq %rdx | [1794]
|
|
|