Searched refs:SLP (Results 1 – 25 of 75) sorted by relevance
123
/external/llvm-project/llvm/test/Transforms/SLPVectorizer/X86/ |
D | opt.ll | 2 …t < %s -O3 -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=SLP 11 ; SLP-LABEL: @test1( 12 ; SLP-NEXT: entry: 13 ; SLP-NEXT: [[TMP0:%.*]] = bitcast double* [[A:%.*]] to <2 x double>* 14 ; SLP-NEXT: [[TMP1:%.*]] = load <2 x double>, <2 x double>* [[TMP0]], align 8 15 ; SLP-NEXT: [[TMP2:%.*]] = bitcast double* [[B:%.*]] to <2 x double>* 16 ; SLP-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8 17 ; SLP-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]] 18 ; SLP-NEXT: [[TMP5:%.*]] = bitcast double* [[C:%.*]] to <2 x double>* 19 ; SLP-NEXT: store <2 x double> [[TMP4]], <2 x double>* [[TMP5]], align 8 [all …]
|
D | remark_unsupported.ll | 5 ; This type is not supported by SLP 49 ; YAML-NEXT: - String: 'Cannot SLP vectorize list: type '
|
D | vector_gep.ll | 7 ; This test checks that SLP vectorizer does not fail on vector GEP.
|
/external/llvm-project/lld/test/ELF/lto/ |
D | slp-vectorize-pm.ll | 4 ; Test SLP and Loop Vectorization are enabled by default at O2 and O3. 5 …pt=O0 --plugin-opt=save-temps -shared -o %t1.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O0-SLP 8 …pt=O1 --plugin-opt=save-temps -shared -o %t2.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O1-SLP 11 …pt=O2 --plugin-opt=save-temps -shared -o %t3.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O2-SLP 14 …pt=O3 --plugin-opt=save-temps -shared -o %t4.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O3-SLP 17 ; CHECK-O0-SLP-NOT: Running pass: SLPVectorizerPass 18 ; CHECK-O1-SLP-NOT: Running pass: SLPVectorizerPass 19 ; CHECK-O2-SLP: Running pass: SLPVectorizerPass 20 ; CHECK-O3-SLP: Running pass: SLPVectorizerPass
|
/external/llvm-project/llvm/test/tools/llvm-lto2/X86/ |
D | slp-vectorize-pm.ll | 3 ; Test SLP and Loop Vectorization are enabled by default at O2 and O3. 5 ; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O0-SLP 9 ; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O1-SLP 13 ; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O2-SLP 17 ; RUN: -use-new-pm -save-temps 2>&1 | FileCheck %s --check-prefix=CHECK-O3-SLP 20 ; CHECK-O0-SLP-NOT: Running pass: SLPVectorizerPass 21 ; CHECK-O1-SLP-NOT: Running pass: SLPVectorizerPass 22 ; CHECK-O2-SLP: Running pass: SLPVectorizerPass 23 ; CHECK-O3-SLP: Running pass: SLPVectorizerPass
|
/external/llvm-project/llvm/test/tools/gold/X86/ |
D | slp-vectorize-pm.ll | 3 ; Test SLP and Loop Vectorization are enabled by default at O2 and O3. 12 ; RUN: -o %t2.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O0-SLP 23 ; RUN: -o %t3.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O1-SLP 34 ; RUN: -o %t4.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O2-SLP 45 ; RUN: -o %t5.o %t.o 2>&1 | FileCheck %s --check-prefix=CHECK-O3-SLP 48 ; CHECK-O0-SLP-NOT: Running pass: SLPVectorizerPass 49 ; CHECK-O1-SLP-NOT: Running pass: SLPVectorizerPass 50 ; CHECK-O2-SLP: Running pass: SLPVectorizerPass 51 ; CHECK-O3-SLP: Running pass: SLPVectorizerPass
|
/external/llvm-project/llvm/test/Other/ |
D | opt-pipeline-vector-passes.ll | 11 ; SLP does not run at -O1. Loop vectorization runs, but it only 16 ; OLDPM_O1-NOT: SLP Vectorizer 23 ; OLDPM_O2: SLP Vectorizer 37 ; OLDPM_O2_EXTRA: SLP Vectorizer 48 ; OLDPM_O1_FORCE_OFF-NOT: SLP Vectorizer 53 ; OLDPM_O2_FORCE_OFF: SLP Vectorizer
|
/external/llvm-project/llvm/test/Transforms/SLPVectorizer/SystemZ/ |
D | SLP-cmp-cost-query.ll | 2 ; RUN: opt -mtriple=systemz-unknown -mcpu=z13 -slp-vectorizer -debug-only=SLP \ 5 ; Check that SLP vectorizer gets the right cost difference for a compare 34 ; CHECK: SLP: Adding cost -1 for bundle that starts with %4 = icmp ult i32 %2, %1.
|
/external/llvm/test/Transforms/SLPVectorizer/X86/ |
D | opt.ll | 1 …t < %s -O3 -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=SLP 9 ; SLP-LABEL: test1 10 ; SLP: store <2 x double>
|
D | vector_gep.ll | 6 ; This test checks that SLP vectorizer does not fail on vector GEP.
|
D | gep.ll | 6 ; Test if SLP can handle GEP expressions.
|
D | saxpy.ll | 6 ; SLP vectorization example from http://cs.stanford.edu/people/eschkufz/research/asplos291-schkufza…
|
/external/skia/experimental/tools/ |
D | web_to_skp | 30 SLP=${4:-0} # sleep in seconds before capture. 4th param iff provided, else 0. 35 (sleep $SLP; printf 'chrome.gpuBenchmarking.printToSkPicture("%s");\nquit\n' "$DST") | \
|
D | web_to_mskp | 30 SLP=${4:-0} # sleep in seconds before capture. 4th param iff provided, else 0. 35 (sleep $SLP; printf 'chrome.gpuBenchmarking.printPagesToSkPictures("%s");\nquit\n' "$DST") | \
|
/external/llvm/docs/ |
D | Vectorizers.rst | 9 which operates on Loops, and the :ref:`SLP Vectorizer 12 The SLP vectorizer merges multiple scalars that are found in the code into 16 Both the Loop Vectorizer and the SLP Vectorizer are enabled by default. 385 The SLP Vectorizer 391 The goal of SLP vectorization (a.k.a. superword-level parallelism) is 407 The SLP-vectorizer processes the code bottom-up, across basic blocks, in search of scalars to combi… 412 The SLP Vectorizer is enabled by default, but it can be disabled
|
/external/llvm-project/llvm/docs/ |
D | Vectorizers.rst | 9 which operates on Loops, and the :ref:`SLP Vectorizer 12 The SLP vectorizer merges multiple scalars that are found in the code into 16 Both the Loop Vectorizer and the SLP Vectorizer are enabled by default. 422 The SLP Vectorizer 428 The goal of SLP vectorization (a.k.a. superword-level parallelism) is 446 The SLP-vectorizer processes the code bottom-up, across basic blocks, in search of scalars to combi… 451 The SLP Vectorizer is enabled by default, but it can be disabled
|
/external/llvm-project/llvm/test/Transforms/SLPVectorizer/AArch64/ |
D | invalid_type.ll | 7 ; CHECK: remark: <unknown>:0:0: Cannot SLP vectorize list: type <16 x i8> is unsupported by vectori…
|
D | mul.ll | 14 ; If we SLP vectorise this then we end up with something like this because we 30 ; If we don't SLP vectorise but scalarize this we get this instead:
|
D | remarks.ll | 12 ; CHECK: remark: /tmp/s.c:5:10: Stores SLP vectorized with cost -4 and with tree size 3
|
D | getelementptr.ll | 28 ; YAML-NEXT: - String: 'SLP vectorized with cost ' 38 ; YAML-NEXT: - String: 'SLP vectorized with cost ' 134 ; YAML-NEXT: - String: 'SLP vectorized with cost ' 144 ; YAML-NEXT: - String: 'SLP vectorized with cost '
|
/external/llvm/test/CodeGen/X86/ |
D | chain_order.ll | 12 ; A test from pifft (after SLP-vectorization) that fails when we drop the chain on newly merged loa…
|
/external/llvm-project/llvm/test/Transforms/SLPVectorizer/ |
D | int_sideeffect.ll | 6 ; SLP vectorization across a @llvm.sideeffect.
|
/external/llvm-project/llvm/test/CodeGen/X86/ |
D | chain_order.ll | 4 ; A test from pifft (after SLP-vectorization) that fails when we drop the chain on newly merged loa…
|
/external/llvm-project/llvm/docs/Proposals/ |
D | VectorizationPlan.rst | 64 b. SLP vectorization. 67 VF and UF), mixed vectorization: vectorizing a loop with SLP patterns 211 1. SLP Vectorizer: one can compare the VPlan model with LLVM's existing SLP
|
/external/llvm-project/llvm/test/Transforms/SLPVectorizer/WebAssembly/ |
D | no-vectorize-rotate.ll | 4 ; Regression test for a bug in the SLP vectorizer that was causing
|
123