Skip to content

[RISCV] Add +optimized-nfN-segment-load-store #114414

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
Nov 3, 2024
Merged

[RISCV] Add +optimized-nfN-segment-load-store #114414

merged 2 commits into from
Nov 3, 2024

Conversation

lukel97
Copy link
Contributor

@lukel97 lukel97 commented Oct 31, 2024 •
edited
Loading

This is a follow up to #111511, where after benchmarking we learnt that the Banana Pi F3 has fast segmented loads for not just NF=2, but also NF=3 and NF=4: https://github.com/preames/bp3-microarch#vlseg_lmul_x_sew_throughput

This adds tuning features to allow these segment loads and stores to be costed cheaper and enables it for the spacemit-x60.

It also enables +optimized-nf2-segment-load-store by default in the generic tuning to maintain the previous behaviour when compiled without -mcpu or -mtune.

@lukel97
[RISCV] Add +optimized-nf{3,4}-segment-load-store
16f895c 
This is a follow up to llvm#111511, where after benchmarking we learnt that the Banana Pi F3 has fast segmented loads for not just NF=2, but also NF=3 and NF=4: https://github.com/preames/bp3-microarch#vlseg_lmul_x_sew_throughput

This adds a tuning feature to allow these segment loads and stores to be costed cheaper and enables it for the spacemit-x60.
@llvmbot
Copy link
Member

llvmbot commented Oct 31, 2024 •
edited
Loading

@llvm/pr-subscribers-llvm-transforms

@llvm/pr-subscribers-backend-risc-v

Author: Luke Lau (lukel97)

Changes

This is a follow up to #111511, where after benchmarking we learnt that the Banana Pi F3 has fast segmented loads for not just NF=2, but also NF=3 and NF=4: https://github.com/preames/bp3-microarch#vlseg_lmul_x_sew_throughput

This adds a tuning feature to allow these segment loads and stores to be costed cheaper and enables it for the spacemit-x60.

Full diff: https://github.com/llvm/llvm-project/pull/114414.diff

4 Files Affected:

  • (modified) llvm/lib/Target/RISCV/RISCVFeatures.td (+7)
  • (modified) llvm/lib/Target/RISCV/RISCVProcessors.td (+3-1)
  • (modified) llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp (+5-2)
  • (modified) llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll (+47-23)
diff --git a/llvm/lib/Target/RISCV/RISCVFeatures.td b/llvm/lib/Target/RISCV/RISCVFeatures.td
index 1e4bf1b8830bcc..719a39944c6836 100644
--- a/llvm/lib/Target/RISCV/RISCVFeatures.td
+++ b/llvm/lib/Target/RISCV/RISCVFeatures.td
@@ -1386,6 +1386,13 @@ def TuneOptimizedZeroStrideLoad
                       "true", "Optimized (perform fewer memory operations)"
                       "zero-stride vector load">;
 
+foreach nf = {3-4} in
+  def TuneOptimizedNF#nf#SegmentLoadStore :
+      SubtargetFeature<"optimized-nf"#nf#"-segment-load-store",
+                       "HasOptimizedNF"#nf#"SegmentLoadStore",
+                       "true", "vlseg"#nf#"eN.v and vsseg"#nf#"eN.v are"
+                       "implemented as a wide memory op and shuffle">;
+
 def Experimental
    : SubtargetFeature<"experimental", "HasExperimental",
                       "true", "Experimental intrinsics">;
diff --git a/llvm/lib/Target/RISCV/RISCVProcessors.td b/llvm/lib/Target/RISCV/RISCVProcessors.td
index 364aa35f09453b..c73bd5e6a1f7ce 100644
--- a/llvm/lib/Target/RISCV/RISCVProcessors.td
+++ b/llvm/lib/Target/RISCV/RISCVProcessors.td
@@ -472,7 +472,9 @@ def SPACEMIT_X60 : RISCVProcessorModel<"spacemit-x60",
                                         FeatureStdExtZvfh,
                                         FeatureStdExtZvkt,
                                         FeatureStdExtZvl256b]),
-                                       [TuneDLenFactor2]>;
+                                       [TuneDLenFactor2,
+                                        TuneOptimizedNF3SegmentLoadStore,
+                                        TuneOptimizedNF4SegmentLoadStore]>;
 
 def RP2350_HAZARD3 : RISCVProcessorModel<"rp2350-hazard3",
                                          NoSchedModel,
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index f050fb569946d6..936e0a9bfdffcc 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -738,8 +738,11 @@ InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
                                             AddressSpace, DL)) {
 
         // Most available hardware today optimizes NF=2 as as one wide memory op
-        // + Factor * LMUL shuffle ops.
-        if (Factor == 2) {
+        // + Factor * LMUL shuffle ops. Some processors may also optimize NF=3
+        // and NF=4.
+        if (Factor == 2 ||
+            (Factor == 3 && ST->hasOptimizedNF3SegmentLoadStore()) ||
+            (Factor == 4 && ST->hasOptimizedNF4SegmentLoadStore())) {
           InstructionCost Cost =
               getMemoryOpCost(Opcode, VTy, Alignment, AddressSpace, CostKind);
           MVT SubVecVT = getTLI()->getValueType(DL, SubVecTy).getSimpleVT();
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
index 6477f14e3c6984..b5f26dd001f884 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
@@ -1,5 +1,7 @@
 ; REQUIRES: asserts
-; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s
+; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,NO-OPT
+; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v,+optimized-nf3-segment-load-store -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,OPT-NF3
+; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v,+optimized-nf4-segment-load-store -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,OPT-NF4
 
 %i8.2 = type {i8, i8}
 define void @i8_factor_2(ptr %data, i64 %n) {
@@ -48,17 +50,28 @@ for.end:
 define void @i8_factor_3(ptr %data, i64 %n) {
 entry:
   br label %for.body
-; CHECK-LABEL: Checking a loop in 'i8_factor_3'
-; CHECK: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 24 for VF 8: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 24 for VF 8: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 48 for VF 16: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 48 for VF 16: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 96 for VF 32: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 96 for VF 32: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; OPT-NF3-LABEL: Checking a loop in 'i8_factor_3'
+; OPT-NF3: Cost of 4 for VF 2: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; OPT-NF3: Cost of 4 for VF 2: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; OPT-NF3: Cost of 4 for VF 4: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; OPT-NF3: Cost of 4 for VF 4: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; OPT-NF3: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; OPT-NF3: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; OPT-NF3: Cost of 7 for VF 16: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; OPT-NF3: Cost of 7 for VF 16: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; OPT-NF3: Cost of 14 for VF 32: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; OPT-NF3: Cost of 14 for VF 32: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; NO-OPT-LABEL: Checking a loop in 'i8_factor_3'
+; NO-OPT: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; NO-OPT: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; NO-OPT: Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; NO-OPT: Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; NO-OPT: Cost of 24 for VF 8: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; NO-OPT: Cost of 24 for VF 8: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; NO-OPT: Cost of 48 for VF 16: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; NO-OPT: Cost of 48 for VF 16: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; NO-OPT: Cost of 96 for VF 32: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; NO-OPT: Cost of 96 for VF 32: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.3, ptr %data, i64 %i, i32 0
@@ -85,17 +98,28 @@ for.end:
 define void @i8_factor_4(ptr %data, i64 %n) {
 entry:
   br label %for.body
-; CHECK-LABEL: Checking a loop in 'i8_factor_4'
-; CHECK: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 16 for VF 4: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 16 for VF 4: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 32 for VF 8: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 32 for VF 8: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 64 for VF 16: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 64 for VF 16: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 128 for VF 32: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 128 for VF 32: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; OPT-NF4-LABEL: Checking a loop in 'i8_factor_4'
+; OPT-NF4: Cost of 5 for VF 2: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; OPT-NF4: Cost of 5 for VF 2: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; OPT-NF4: Cost of 5 for VF 4: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; OPT-NF4: Cost of 5 for VF 4: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; OPT-NF4: Cost of 6 for VF 8: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; OPT-NF4: Cost of 6 for VF 8: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; OPT-NF4: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; OPT-NF4: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; OPT-NF4: Cost of 16 for VF 32: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; OPT-NF4: Cost of 16 for VF 32: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; NO-OPT-LABEL: Checking a loop in 'i8_factor_4'
+; NO-OPT: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; NO-OPT: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; NO-OPT: Cost of 16 for VF 4: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; NO-OPT: Cost of 16 for VF 4: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; NO-OPT: Cost of 32 for VF 8: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; NO-OPT: Cost of 32 for VF 8: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; NO-OPT: Cost of 64 for VF 16: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; NO-OPT: Cost of 64 for VF 16: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; NO-OPT: Cost of 128 for VF 32: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; NO-OPT: Cost of 128 for VF 32: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.4, ptr %data, i64 %i, i32 0

@lukel97
Copy link
Contributor Author

lukel97 commented Oct 31, 2024

cc @camel-cdr

preames
preames reviewed Oct 31, 2024
View reviewed changes
@lukel97 lukel97 changed the title [RISCV] Add +optimized-nf{3,4}-segment-load-store [RISCV] Add +optimized-nfN-segment-load-store Oct 31, 2024
preames
preames reviewed Oct 31, 2024
View reviewed changes
llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v,+optimized-nf3-segment-load-store -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,OPT-NF3
; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v,+optimized-nf4-segment-load-store -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,OPT-NF4
; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v,-optimized-nf2-segment-load-store -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=NO-OPT
; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=OPT-NF2
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you swapped your runlines vs checks for this line and the one above.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

+optimized-nf2-segment-load-store is enabled by default with the generic tuning, so the first run line is a negative feature to turn it off. The second run line actually has it enabled but I could make it explicit here if prefered

wangpc-pp
wangpc-pp reviewed Nov 1, 2024
View reviewed changes
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
static bool hasOptimizedSegmentLoadStore(unsigned NF,
const RISCVSubtarget *ST) {
switch (NF) {
case 2:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Save some lines via using macros?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I considered it but remembered coming across some PRs where people were actively trying to remove uses of macros in LLVM, e.g. #105551

I'm not strongly opinionated on this, is there a general stance we should take here?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is there a general stance we should take here?

Not found in https://llvm.org/docs/CodingStandards.html. I think it's OK not to use macros here, just a weak suggestion.

llvm/lib/Target/RISCV/RISCVFeatures.td
@@ -1386,6 +1386,13 @@ def TuneOptimizedZeroStrideLoad
"true", "Optimized (perform fewer memory operations)"
"zero-stride vector load">;

foreach nf = {2-8} in
def TuneOptimizedNF#nf#SegmentLoadStore :
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A random thought: There are 250 features for RISCV now, we may need to increase MAX_SUBTARGET_FEATURES soon.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Isn't the limit 5*64 or 320?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, but that won't last long, especially if we add some fusions (like XiangShan).

wangpc-pp
wangpc-pp approved these changes Nov 1, 2024
View reviewed changes
Copy link
Contributor

@wangpc-pp wangpc-pp left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM.

preames
preames approved these changes Nov 1, 2024
View reviewed changes
Copy link
Collaborator

@preames preames left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@zqb-all
Copy link
Contributor

zqb-all commented Nov 3, 2024

LGTM

@lukel97 lukel97 merged commit beb12f9 into llvm:main Nov 3, 2024
8 checks passed
@llvm-ci
Copy link
Collaborator

llvm-ci commented Nov 3, 2024

LLVM Buildbot has detected a new failure on builder openmp-offload-libc-amdgpu-runtime running on omp-vega20-1 while building llvm at step 10 "Add check check-offload".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/73/builds/7969

Here is the relevant piece of the build log for the reference 
Step 10 (Add check check-offload) failure: 1200 seconds without output running [b'ninja', b'-j 32', b'check-offload'], attempting to kill
...
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/wtime.c (866 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/bug49779.cpp (867 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/bug47654.cpp (868 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/test_libc.cpp (869 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/bug50022.cpp (870 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu :: offloading/bug49021.cpp (871 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu :: offloading/std_complex_arithmetic.cpp (872 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/complex_reduction.cpp (873 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/bug49021.cpp (874 of 879)
PASS: libomptarget :: x86_64-unknown-linux-gnu-LTO :: offloading/std_complex_arithmetic.cpp (875 of 879)
command timed out: 1200 seconds without output running [b'ninja', b'-j 32', b'check-offload'], attempting to kill
process killed by signal 9
program finished with exit code -1
elapsedTime=1238.569488

@llvm-ci
Copy link
Collaborator

llvm-ci commented Nov 4, 2024

LLVM Buildbot has detected a new failure on builder clang-ppc64-aix running on aix-ppc64 while building llvm at step 6 "test-build-unified-tree-check-all".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/64/builds/1363

Here is the relevant piece of the build log for the reference 
Step 6 (test-build-unified-tree-check-all) failure: test (failure)
******************** TEST 'lit :: googletest-timeout.py' FAILED ********************
Exit Code: 1

Command Output (stdout):
--
# RUN: at line 9
not env -u FILECHECK_OPTS "/opt/freeware/bin/python3.9" /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit.py -j1 --order=lexical -v Inputs/googletest-timeout    --param gtest_filter=InfiniteLoopSubTest --timeout=1 > /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/Output/googletest-timeout.py.tmp.cmd.out
# executed command: not env -u FILECHECK_OPTS /opt/freeware/bin/python3.9 /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit.py -j1 --order=lexical -v Inputs/googletest-timeout --param gtest_filter=InfiniteLoopSubTest --timeout=1
# .---command stderr------------
# | lit.py: /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit/main.py:72: note: The test suite configuration requested an individual test timeout of 0 seconds but a timeout of 1 seconds was requested on the command line. Forcing timeout to be 1 seconds.
# `-----------------------------
# RUN: at line 11
FileCheck --check-prefix=CHECK-INF < /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/Output/googletest-timeout.py.tmp.cmd.out /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/googletest-timeout.py
# executed command: FileCheck --check-prefix=CHECK-INF /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/googletest-timeout.py
# RUN: at line 16
not env -u FILECHECK_OPTS "/opt/freeware/bin/python3.9" /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit.py -j1 --order=lexical -v Inputs/googletest-timeout   --param gtest_filter=InfiniteLoopSubTest  --param set_timeout=1   > /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/Output/googletest-timeout.py.tmp.cfgset.out
# executed command: not env -u FILECHECK_OPTS /opt/freeware/bin/python3.9 /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit.py -j1 --order=lexical -v Inputs/googletest-timeout --param gtest_filter=InfiniteLoopSubTest --param set_timeout=1
# .---command stderr------------
# | Traceback (most recent call last):
# |   File "/home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit/formats/googletest.py", line 304, in post_process_shard_results
# |     testsuites = json.load(f)["testsuites"]
# |   File "/opt/freeware/lib64/python3.9/json/__init__.py", line 293, in load
# |     return loads(fp.read(),
# |   File "/opt/freeware/lib64/python3.9/json/__init__.py", line 346, in loads
# |     return _default_decoder.decode(s)
# |   File "/opt/freeware/lib64/python3.9/json/decoder.py", line 337, in decode
# |     obj, end = self.raw_decode(s, idx=_w(s, 0).end())
# |   File "/opt/freeware/lib64/python3.9/json/decoder.py", line 355, in raw_decode
# |     raise JSONDecodeError("Expecting value", s, err.value) from None
# | json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
# | 
# | During handling of the above exception, another exception occurred:
# | 
# | Traceback (most recent call last):
# |   File "/home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit.py", line 6, in <module>
# |     main()
# |   File "/home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit/main.py", line 130, in main
# |     selected_tests, discovered_tests = GoogleTest.post_process_shard_results(
# |   File "/home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/llvm-project/llvm/utils/lit/lit/formats/googletest.py", line 306, in post_process_shard_results
# |     raise RuntimeError(
# | RuntimeError: Failed to parse json file: /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/Inputs/googletest-timeout/DummySubDir/OneTest.py-googletest-timeout-58393082-1-2.json
# | 
# `-----------------------------
# RUN: at line 19
FileCheck --check-prefix=CHECK-INF < /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/Output/googletest-timeout.py.tmp.cfgset.out /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/googletest-timeout.py
# executed command: FileCheck --check-prefix=CHECK-INF /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/googletest-timeout.py
# .---command stderr------------
# | /home/powerllvm/powerllvm_env/aix-ppc64/clang-ppc64-aix/build/utils/lit/tests/googletest-timeout.py:34:14: error: CHECK-INF: expected string not found in input
# | # CHECK-INF: Timed Out: 1
# |              ^
...

PhilippRados pushed a commit to PhilippRados/llvm-project that referenced this pull request Nov 6, 2024
@lukel97 @PhilippRados
[RISCV] Add +optimized-nfN-segment-load-store (llvm#114414)
8704c36 
This is a follow up to llvm#111511, where after benchmarking we learnt that
the Banana Pi F3 has fast segmented loads for not just NF=2, but also
NF=3 and NF=4:
https://github.com/preames/bp3-microarch#vlseg_lmul_x_sew_throughput

This adds tuning features to allow these segment loads and stores to be
costed cheaper and enables it for the spacemit-x60.

It also enables +optimized-nf2-segment-load-store by default in the
generic tuning to maintain the previous behaviour when compiled without
-mcpu or -mtune.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@preames preames preames approved these changes

@wangpc-pp wangpc-pp wangpc-pp approved these changes

@topperc topperc Awaiting requested review from topperc

Assignees
No one assigned
Labels
backend:RISC-V llvm:transforms
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@lukel97 @llvmbot @zqb-all @llvm-ci @preames @topperc @wangpc-pp