RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 02:33:06 +01:00
Code Issues Projects Releases Wiki Activity

[MCA][InstrBuilder] Correctly mark reserved resources in initializeUsedResources.

Browse Source 
This fixes a bug reported by Alex Renda on LLVMDev where mca did not correctly
mark a resource group as "reserved".
(See http://lists.llvm.org/pipermail/llvm-dev/2020-May/141485.html).

The issue was caused by a wrong check in function `initializeUsedResources`.
As a consequence of this, a resource group was left unreserved, and its field
`NumUnits` incorrectly reported an unrealistic number of consumed resource
units.

This patch fixes the issue with the handling of reserved resources in the
InstrBuilder class, and adds a simple test for it.  Ideally, as suggested by
Andy Trick, most of these problems will disappear if in the future we will
introduce a (optional) DelayCycles vector for SchedWriteRes.
This commit is contained in:
Andrea Di Biagio 2020-05-10 18:55:58 +01:00
parent 0e4a65ecbd
commit 79ed672fa3
2 changed files with 49 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/MCA/InstrBuilder.cpp
View File

@ -160,8 +160,11 @@ static void initializeUsedResources(InstrDesc &ID,
if (countPopulation(RPC.first) > 1 && !RPC.second.isReserved()) {
// Remove the leading 1 from the resource group mask.
uint64_t Mask = RPC.first ^ PowerOf2Floor(RPC.first);
if ((Mask & UsedResourceUnits) == Mask)
uint64_t MaxResourceUnits = countPopulation(Mask);
if (RPC.second.NumUnits > countPopulation(Mask)) {
RPC.second.setReserved();
RPC.second.NumUnits = MaxResourceUnits;
}
}
}

45
test/tools/llvm-mca/X86/Haswell/reserved-resources.s Normal file
View File

@ -0,0 +1,45 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=haswell -iterations=100 < %s | FileCheck %s
fxrstor (%rsp)
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 100
# CHECK-NEXT: Total Cycles: 6403
# CHECK-NEXT: Total uOps: 9000
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.41
# CHECK-NEXT: IPC: 0.02
# CHECK-NEXT: Block RThroughput: 22.5
# 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: 90 64 16.50 * * U fxrstor (%rsp)
# CHECK: Resources:
# CHECK-NEXT: [0] - HWDivider
# CHECK-NEXT: [1] - HWFPDivider
# CHECK-NEXT: [2] - HWPort0
# CHECK-NEXT: [3] - HWPort1
# CHECK-NEXT: [4] - HWPort2
# CHECK-NEXT: [5] - HWPort3
# CHECK-NEXT: [6] - HWPort4
# CHECK-NEXT: [7] - HWPort5
# CHECK-NEXT: [8] - HWPort6
# CHECK-NEXT: [9] - HWPort7
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
# CHECK-NEXT: - - 4.00 1.00 16.50 16.50 - 1.00 2.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
# CHECK-NEXT: - - 4.00 1.00 16.50 16.50 - 1.00 2.00 - fxrstor (%rsp)