maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[MCA] Support in-order CPUs with MicroOpBufferSize=1 

Differential Revision: https://reviews.llvm.org/D98356
This commit is contained in:
Jay Foad 2021-03-09 16:12:36 +00:00
parent 403da6a69a
commit 7340fd6886
3 changed files with 73 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/lib/MCA/HardwareUnits/RetireControlUnit.cpp
View File

@ -21,8 +21,8 @@ namespace mca {
RetireControlUnit::RetireControlUnit(const MCSchedModel &SM)
: NextAvailableSlotIdx(0), CurrentInstructionSlotIdx(0),
NumROBEntries(SM.MicroOpBufferSize),
AvailableEntries(SM.MicroOpBufferSize), MaxRetirePerCycle(0) {
AvailableEntries(SM.isOutOfOrder() ? SM.MicroOpBufferSize : 0),
MaxRetirePerCycle(0) {
// Check if the scheduling model provides extra information about the machine
// processor. If so, then use that information to set the reorder buffer size
// and the maximum number of instructions retired per cycle.
@ -33,8 +33,7 @@ RetireControlUnit::RetireControlUnit(const MCSchedModel &SM)
MaxRetirePerCycle = EPI.MaxRetirePerCycle;
}
NumROBEntries = AvailableEntries;
bool IsOutOfOrder = SM.MicroOpBufferSize;
if (!IsOutOfOrder && !NumROBEntries)
if (!SM.isOutOfOrder() && !NumROBEntries)
return;
assert(NumROBEntries && "Invalid reorder buffer size!");
Queue.resize(2 * NumROBEntries);

68
llvm/test/tools/llvm-mca/AMDGPU/gfx10-add-sequence.s Normal file
View File

@ -0,0 +1,68 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=amdgcn -mcpu=gfx1010 --timeline --iterations=1 < %s | FileCheck %s
v_add_f32 v0, v0, v0
v_add_f32 v1, v1, v1
v_add_f32 v2, v1, v0
# CHECK: Iterations: 1
# CHECK-NEXT: Instructions: 3
# CHECK-NEXT: Total Cycles: 13
# CHECK-NEXT: Total uOps: 3
# CHECK: Dispatch Width: 1
# CHECK-NEXT: uOps Per Cycle: 0.23
# CHECK-NEXT: IPC: 0.23
# CHECK-NEXT: Block RThroughput: 3.0
# 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 5 1.00 U v_add_f32_e32 v0, v0, v0
# CHECK-NEXT: 1 5 1.00 U v_add_f32_e32 v1, v1, v1
# CHECK-NEXT: 1 5 1.00 U v_add_f32_e32 v2, v1, v0
# CHECK: Resources:
# CHECK-NEXT: [0] - HWBranch
# CHECK-NEXT: [1] - HWExport
# CHECK-NEXT: [2] - HWLGKM
# CHECK-NEXT: [3] - HWRC
# CHECK-NEXT: [4] - HWSALU
# CHECK-NEXT: [5] - HWVALU
# CHECK-NEXT: [6] - HWVMEM
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6]
# CHECK-NEXT: - - - 3.00 - 3.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: - - - 1.00 - 1.00 - v_add_f32_e32 v0, v0, v0
# CHECK-NEXT: - - - 1.00 - 1.00 - v_add_f32_e32 v1, v1, v1
# CHECK-NEXT: - - - 1.00 - 1.00 - v_add_f32_e32 v2, v1, v0
# CHECK: Timeline view:
# CHECK-NEXT: 012
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeeER . . v_add_f32_e32 v0, v0, v0
# CHECK-NEXT: [0,1] .DeeeeER . . v_add_f32_e32 v1, v1, v1
# CHECK-NEXT: [0,2] . .DeeeeER v_add_f32_e32 v2, v1, v0
# CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 0.0 0.0 0.0 v_add_f32_e32 v0, v0, v0
# CHECK-NEXT: 1. 1 0.0 0.0 0.0 v_add_f32_e32 v1, v1, v1
# CHECK-NEXT: 2. 1 0.0 0.0 0.0 v_add_f32_e32 v2, v1, v0
# CHECK-NEXT: 1 0.0 0.0 0.0 <total>

2
llvm/test/tools/llvm-mca/AMDGPU/lit.local.cfg Normal file
View File

@ -0,0 +1,2 @@
if not 'AMDGPU' in config.root.targets:
config.unsupported = True