ScheduleOptimizer: Allow to set register width in command line

We use this option to set a fixed register width in our test cases to make
sure the results are identical accross platforms.

llvm-svn: 292002

Author: tobiasgrosser

polly/lib/Transform/ScheduleOptimizer.cpp

@@ -162,6 +162,12 @@ static cl::opt<int> SecondCacheLevelSize(
     cl::desc("The size of the second level specified in bytes."), cl::Hidden,
     cl::init(262144), cl::ZeroOrMore, cl::cat(PollyCategory));
 
+static cl::opt<int> VectorRegisterBitwidth(
+    "polly-target-vector-register-bitwidth",
+    cl::desc("The size in bits of a vector register (if not set, this "
+             "information is taken from LLVM's target information."),
+    cl::Hidden, cl::init(-1), cl::ZeroOrMore, cl::cat(PollyCategory));
+
 static cl::opt<int> FirstLevelDefaultTileSize(
     "polly-default-tile-size",
     cl::desc("The default tile size (if not enough were provided by"
@@ -599,7 +605,11 @@ getMicroKernelParams(const llvm::TargetTransformInfo *TTI) {
 
   // Nvec - Number of double-precision floating-point numbers that can be hold
   // by a vector register. Use 2 by default.
-  auto Nvec = TTI->getRegisterBitWidth(true) / 64;
+  long RegisterBitwidth = VectorRegisterBitwidth;
+
+  if (RegisterBitwidth == -1)
+    RegisterBitwidth = TTI->getRegisterBitWidth(true);
+  auto Nvec = RegisterBitwidth / 64;
   if (Nvec == 0)
     Nvec = 2;
   int Nr =

polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout.ll

@@ -1,4 +1,13 @@
-; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -polly-target-throughput-vector-fma=1 -polly-target-latency-vector-fma=8 -polly-target-1st-cache-level-associativity=8 -polly-target-2nd-cache-level-associativity=8 -polly-target-1st-cache-level-size=32768 -polly-target-2nd-cache-level-size=262144 -polly-optimized-scops < %s 2>&1 | FileCheck %s
+; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true \
+; RUN: -polly-target-throughput-vector-fma=1 \
+; RUN: -polly-target-latency-vector-fma=8 \
+; RUN: -polly-target-1st-cache-level-associativity=8 \
+; RUN: -polly-target-2nd-cache-level-associativity=8 \
+; RUN: -polly-target-1st-cache-level-size=32768 \
+; RUN: -polly-target-2nd-cache-level-size=262144 \
+; RUN: -polly-optimized-scops \
+; RUN: -polly-target-vector-register-bitwidth=256 \
+; RUN: < %s 2>&1 | FileCheck %s
 ;
 ;    /* C := alpha*A*B + beta*C */
 ;    for (i = 0; i < _PB_NI; i++)

polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout_2.ll

@@ -1,4 +1,12 @@
-; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -polly-target-throughput-vector-fma=1 -polly-target-latency-vector-fma=8 -polly-target-1st-cache-level-associativity=8 -polly-target-2nd-cache-level-associativity=8 -polly-target-1st-cache-level-size=32768 -polly-target-2nd-cache-level-size=262144 -polly-ast -analyze < %s | FileCheck %s
+; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true \
+; RUN: -polly-target-throughput-vector-fma=1 \
+; RUN: -polly-target-latency-vector-fma=8 \
+; RUN: -polly-target-1st-cache-level-associativity=8 \
+; RUN: -polly-target-2nd-cache-level-associativity=8 \
+; RUN: -polly-target-1st-cache-level-size=32768 \
+; RUN: -polly-target-2nd-cache-level-size=262144 -polly-ast \
+; RUN: -polly-target-vector-register-bitwidth=256 \
+; RUN:  -analyze < %s | FileCheck %s
 ;
 ;    /* C := alpha*A*B + beta*C */
 ;    /* _PB_NK % Kc != 0 */

polly/test/ScheduleOptimizer/pattern-matching-based-opts_3.ll

@@ -1,5 +1,19 @@
-; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -polly-target-throughput-vector-fma=1 -polly-target-latency-vector-fma=8 -analyze -polly-ast -polly-target-1st-cache-level-size=0 < %s 2>&1 | FileCheck %s
-; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -polly-target-throughput-vector-fma=1 -polly-target-latency-vector-fma=8 -analyze -polly-ast -polly-target-1st-cache-level-associativity=8 -polly-target-2nd-cache-level-associativity=8 -polly-target-1st-cache-level-size=32768 -polly-target-2nd-cache-level-size=262144 < %s 2>&1 | FileCheck %s --check-prefix=EXTRACTION-OF-MACRO-KERNEL
+; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true \
+; RUN: -polly-target-throughput-vector-fma=1 \
+; RUN: -polly-target-latency-vector-fma=8 \
+; RUN: -analyze -polly-ast -polly-target-1st-cache-level-size=0 \
+; RUN: -polly-target-vector-register-bitwidth=256 \
+; RUN: < %s 2>&1 | FileCheck %s
+
+; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true \
+; RUN: -polly-target-throughput-vector-fma=1 \
+; RUN: -polly-target-latency-vector-fma=8 \
+; RUN: -analyze -polly-ast -polly-target-1st-cache-level-associativity=8 \
+; RUN: -polly-target-2nd-cache-level-associativity=8 \
+; RUN: -polly-target-1st-cache-level-size=32768 \
+; RUN: -polly-target-vector-register-bitwidth=256 \
+; RUN: -polly-target-2nd-cache-level-size=262144 < %s 2>&1 \
+; RUN: | FileCheck %s --check-prefix=EXTRACTION-OF-MACRO-KERNEL
 ;
 ;    /* C := alpha*A*B + beta*C */
 ;    for (i = 0; i < _PB_NI; i++)