mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 03:33:20 +01:00
38b78fd66c
Single operand MUL instructions that implicitly set EAX have the following latency/throughput profile (see below): imul %cl # latency: 3cy - uOPs: 1 - 1 JMul imul %cx # latency: 3cy - uOPs: 3 - 3 JMul imul %ecx # latency: 3cy - uOPs: 2 - 2 JMul imul %rcx # latency: 6cy - uOPs: 2 - 4 JMul mul %cl # latency: 3cy - uOPs: 1 - 1 JMul mul %cx # latency: 3cy - uOPs: 3 - 3 JMul mul %ecx # latency: 3cy - uOPs: 2 - 2 JMul mul %rcx # latency: 6cy - uOPs: 2 - 4 JMul Excluding the 64bit variant, which has a latency of 6cy, every other instruction has a latency of 3cy. However, the number of decoded macro-opcodes (as well as the resource cyles) depend on the MUL size. The two operand MULs have a more predictable profile (see below): imul %dx, %dx # latency: 3cy - uOPs: 1 - 1 JMul imul %edx, %edx # latency: 3cy - uOPs: 1 - 1 JMul imul %rdx, %rdx # latency: 6cy - uOPs: 1 - 4 JMul imul $3, %dx, %dx # latency: 4cy - uOPs: 2 - 2 JMul imul $3, %ecx, %ecx # latency: 3cy - uOPs: 1 - 1 JMul imul $3, %rdx, %rdx # latency: 6cy - uOPs: 1 - 4 JMul This patch updates the values in the Jaguar scheduling model and regenerates llvm-mca tests. Differential Revision: https://reviews.llvm.org/D66547 llvm-svn: 369661
111 lines
4.0 KiB
ArmAsm
111 lines
4.0 KiB
ArmAsm
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 < %s | FileCheck %s
|
|
|
|
testloop:
|
|
# LLVM-MCA-BEGIN upper
|
|
leal 42(%rdi), %eax
|
|
# LLVM-MCA-BEGIN lower
|
|
imull %esi, %eax
|
|
# LLVM-MCA-END upper
|
|
leal 42(%rdi), %eax
|
|
# LLVM-MCA-END lower
|
|
imull %esi, %eax
|
|
|
|
# CHECK: [0] Code Region - upper
|
|
|
|
# CHECK: Iterations: 100
|
|
# CHECK-NEXT: Instructions: 200
|
|
# CHECK-NEXT: Total Cycles: 106
|
|
# CHECK-NEXT: Total uOps: 200
|
|
|
|
# CHECK: Dispatch Width: 2
|
|
# CHECK-NEXT: uOps Per Cycle: 1.89
|
|
# CHECK-NEXT: IPC: 1.89
|
|
# CHECK-NEXT: Block RThroughput: 1.0
|
|
|
|
# CHECK: Instruction Info:
|
|
# CHECK-NEXT: [1]: #uOps
|
|
# CHECK-NEXT: [2]: Latency
|
|
# CHECK-NEXT: [3]: RThroughput
|
|
# CHECK-NEXT: [4]: MayLoad
|
|
# CHECK-NEXT: [5]: MayStore
|
|
# CHECK-NEXT: [6]: HasSideEffects (U)
|
|
|
|
# CHECK: [1] [2] [3] [4] [5] [6] Instructions:
|
|
# CHECK-NEXT: 1 1 0.50 leal 42(%rdi), %eax
|
|
# CHECK-NEXT: 1 3 1.00 imull %esi, %eax
|
|
|
|
# CHECK: Resources:
|
|
# CHECK-NEXT: [0] - JALU0
|
|
# CHECK-NEXT: [1] - JALU1
|
|
# CHECK-NEXT: [2] - JDiv
|
|
# CHECK-NEXT: [3] - JFPA
|
|
# CHECK-NEXT: [4] - JFPM
|
|
# CHECK-NEXT: [5] - JFPU0
|
|
# CHECK-NEXT: [6] - JFPU1
|
|
# CHECK-NEXT: [7] - JLAGU
|
|
# CHECK-NEXT: [8] - JMul
|
|
# CHECK-NEXT: [9] - JSAGU
|
|
# CHECK-NEXT: [10] - JSTC
|
|
# CHECK-NEXT: [11] - JVALU0
|
|
# CHECK-NEXT: [12] - JVALU1
|
|
# CHECK-NEXT: [13] - JVIMUL
|
|
|
|
# CHECK: Resource pressure per iteration:
|
|
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
|
|
# CHECK-NEXT: 0.99 1.01 - - - - - - 1.00 - - - - -
|
|
|
|
# CHECK: Resource pressure by instruction:
|
|
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
|
|
# CHECK-NEXT: 0.99 0.01 - - - - - - - - - - - - leal 42(%rdi), %eax
|
|
# CHECK-NEXT: - 1.00 - - - - - - 1.00 - - - - - imull %esi, %eax
|
|
|
|
# CHECK: [1] Code Region - lower
|
|
|
|
# CHECK: Iterations: 100
|
|
# CHECK-NEXT: Instructions: 200
|
|
# CHECK-NEXT: Total Cycles: 105
|
|
# CHECK-NEXT: Total uOps: 200
|
|
|
|
# CHECK: Dispatch Width: 2
|
|
# CHECK-NEXT: uOps Per Cycle: 1.90
|
|
# CHECK-NEXT: IPC: 1.90
|
|
# CHECK-NEXT: Block RThroughput: 1.0
|
|
|
|
# CHECK: Instruction Info:
|
|
# CHECK-NEXT: [1]: #uOps
|
|
# CHECK-NEXT: [2]: Latency
|
|
# CHECK-NEXT: [3]: RThroughput
|
|
# CHECK-NEXT: [4]: MayLoad
|
|
# CHECK-NEXT: [5]: MayStore
|
|
# CHECK-NEXT: [6]: HasSideEffects (U)
|
|
|
|
# CHECK: [1] [2] [3] [4] [5] [6] Instructions:
|
|
# CHECK-NEXT: 1 3 1.00 imull %esi, %eax
|
|
# CHECK-NEXT: 1 1 0.50 leal 42(%rdi), %eax
|
|
|
|
# CHECK: Resources:
|
|
# CHECK-NEXT: [0] - JALU0
|
|
# CHECK-NEXT: [1] - JALU1
|
|
# CHECK-NEXT: [2] - JDiv
|
|
# CHECK-NEXT: [3] - JFPA
|
|
# CHECK-NEXT: [4] - JFPM
|
|
# CHECK-NEXT: [5] - JFPU0
|
|
# CHECK-NEXT: [6] - JFPU1
|
|
# CHECK-NEXT: [7] - JLAGU
|
|
# CHECK-NEXT: [8] - JMul
|
|
# CHECK-NEXT: [9] - JSAGU
|
|
# CHECK-NEXT: [10] - JSTC
|
|
# CHECK-NEXT: [11] - JVALU0
|
|
# CHECK-NEXT: [12] - JVALU1
|
|
# CHECK-NEXT: [13] - JVIMUL
|
|
|
|
# CHECK: Resource pressure per iteration:
|
|
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
|
|
# CHECK-NEXT: 1.00 1.00 - - - - - - 1.00 - - - - -
|
|
|
|
# CHECK: Resource pressure by instruction:
|
|
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
|
|
# CHECK-NEXT: - 1.00 - - - - - - 1.00 - - - - - imull %esi, %eax
|
|
# CHECK-NEXT: 1.00 - - - - - - - - - - - - - leal 42(%rdi), %eax
|