Change the determination of parameters of macro-kernel

Typically processor architectures do not include an L3 cache, which means that
Nc, the parameter of the micro-kernel, is, for all practical purposes,
redundant ([1]). However, its small values can cause the redundant packing of
the same elements of the matrix A, the first operand of the matrix
multiplication. At the same time, big values of the parameter Nc can cause
segmentation faults in case the available stack is exceeded.

This patch adds an option to specify the parameter Nc as a multiple of
the parameter of the micro-kernel Nr.

In case of Intel Core i7-3820 SandyBridge and the following options,

clang -O3 gemm.c -I utilities/ utilities/polybench.c -DPOLYBENCH_TIME
-march=native -mllvm -polly -mllvm -polly-pattern-matching-based-opts=true
-DPOLYBENCH_USE_SCALAR_LB -mllvm -polly-target-cache-level-associativity=8,8
-mllvm -polly-target-cache-level-sizes=32768,262144 -mllvm
-polly-target-latency-vector-fma=8

it helps to improve the performance from 11.303 GFlops/sec (39,247% of
theoretical peak) to 17.896 GFlops/sec (62,14% of theoretical peak).

Refs.:

[1] - http://www.cs.utexas.edu/users/flame/pubs/TOMS-BLIS-Analytical.pdf

Reviewed-by: Tobias Grosser <tobias@grosser.es>

Differential Revision: https://reviews.llvm.org/D28019

llvm-svn: 290256

4 files changed, 109 insertions, 102 deletions

diff --git a/polly/lib/Transform/ScheduleOptimizer.cpp b/polly/lib/Transform/ScheduleOptimizer.cpp
index ae7d733124c..54e3d8d08af 100644
--- a/polly/lib/Transform/ScheduleOptimizer.cpp
+++ b/polly/lib/Transform/ScheduleOptimizer.cpp
@@ -185,6 +185,12 @@ static cl::opt<int> RegisterDefaultTileSize(
              " --polly-register-tile-sizes)"),
     cl::Hidden, cl::init(2), cl::ZeroOrMore, cl::cat(PollyCategory));
 
+static cl::opt<int> PollyPatternMatchingNcQuotient(
+    "polly-pattern-matching-nc-quotient",
+    cl::desc("Quotient that is obtained by dividing Nc, the parameter of the"
+             "macro-kernel, by Nr, the parameter of the micro-kernel"),
+    cl::Hidden, cl::init(256), cl::ZeroOrMore, cl::cat(PollyCategory));
+
 static cl::list<int>
     RegisterTileSizes("polly-register-tile-sizes",
                       cl::desc("A tile size for each loop dimension, filled "
@@ -610,6 +616,9 @@ getMacroKernelParams(const MicroKernelParamsTy &MicroKernelParams) {
         CacheLevelSizes[0] > 0 && CacheLevelSizes[1] > 0 &&
         CacheLevelAssociativity[0] > 2 && CacheLevelAssociativity[1] > 2))
     return {1, 1, 1};
+  // The quotient should be greater than zero.
+  if (PollyPatternMatchingNcQuotient <= 0)
+    return {1, 1, 1};
   int Car = floor(
       (CacheLevelAssociativity[0] - 1) /
       (1 + static_cast<double>(MicroKernelParams.Nr) / MicroKernelParams.Mr));
@@ -618,7 +627,7 @@ getMacroKernelParams(const MicroKernelParamsTy &MicroKernelParams) {
   double Cac = static_cast<double>(Kc * 8 * CacheLevelAssociativity[1]) /
                CacheLevelSizes[1];
   int Mc = floor((CacheLevelAssociativity[1] - 2) / Cac);
-  int Nc = floor(1 / Cac);
+  int Nc = PollyPatternMatchingNcQuotient * MicroKernelParams.Nr;
   return {Mc, Nc, Kc};
 }
 
diff --git a/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout.ll b/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout.ll
index e7a1dc82973..4f723c59d85 100644
--- a/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout.ll
+++ b/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout.ll
@@ -9,14 +9,14 @@
 ;	     C[i][j] += alpha * A[i][k] * B[k][j];
 ;        }
 ;
-; CHECK:        double Packed_B[ { [] -> [(2)] } ][ { [] -> [(256)] } ][ { [] -> [(8)] } ]; // Element size 8
+; CHECK:        double Packed_B[ { [] -> [(256)] } ][ { [] -> [(256)] } ][ { [] -> [(8)] } ];
 ; CHECK-NEXT:        double Packed_A[ { [] -> [(24)] } ][ { [] -> [(256)] } ][ { [] -> [(4)] } ]; // Element size 8
 ;
 ; CHECK:                { Stmt_Copy_0[i0, i1, i2] -> MemRef_arg6[i0, i2] };
 ; CHECK-NEXT:           new: { Stmt_Copy_0[i0, i1, i2] -> Packed_A[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 4*floor((-i0 + o2)/4) = -i0 + o2 and 0 <= o1 <= 255 and 0 <= o2 <= 3 and -3 + i0 - 4o0 <= 96*floor((i0)/96) <= i0 - 4o0 };
 ;
 ; CHECK:                { Stmt_Copy_0[i0, i1, i2] -> MemRef_arg7[i2, i1] };
-; CHECK-NEXT:           new: { Stmt_Copy_0[i0, i1, i2] -> Packed_B[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 8*floor((-i1 + o2)/8) = -i1 + o2 and 0 <= o1 <= 255 and 0 <= o2 <= 7 and -7 + i1 - 8o0 <= 16*floor((i1)/16) <= i1 - 8o0 };
+; CHECK-NEXT:           new: { Stmt_Copy_0[i0, i1, i2] -> Packed_B[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 8*floor((-i1 + o2)/8) = -i1 + o2 and 0 <= o1 <= 255 and 0 <= o2 <= 7 and -7 + i1 - 8o0 <= 2048*floor((i1)/2048) <= i1 - 8o0 };
 ;
 ; CHECK:    	CopyStmt_0
 ; CHECK-NEXT:            Domain :=
@@ -25,7 +25,7 @@
 ; CHECK-NEXT:                ;
 ; CHECK-NEXT:            MustWriteAccess :=	[Reduction Type: NONE] [Scalar: 0]
 ; CHECK-NEXT:                null;
-; CHECK-NEXT:           new: { CopyStmt_0[i0, i1, i2] -> Packed_B[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 8*floor((-i1 + o2)/8) = -i1 + o2 and 0 <= o1 <= 255 and 0 <= o2 <= 7 and -7 + i1 - 8o0 <= 16*floor((i1)/16) <= i1 - 8o0 };
+; CHECK-NEXT:           new: { CopyStmt_0[i0, i1, i2] -> Packed_B[o0, o1, o2] : 256*floor((-i2 + o1)/256) = -i2 + o1 and 8*floor((-i1 + o2)/8) = -i1 + o2 and 0 <= o1 <= 255 and 0 <= o2 <= 7 and -7 + i1 - 8o0 <= 2048*floor((i1)/2048) <= i1 - 8o0 };
 ; CHECK-NEXT:            ReadAccess :=	[Reduction Type: NONE] [Scalar: 0]
 ; CHECK-NEXT:                null;
 ; CHECK-NEXT:           new: { CopyStmt_0[i0, i1, i2] -> MemRef_arg7[i2, i1] };
diff --git a/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout_2.ll b/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout_2.ll
index 9ff8da198cc..73d48e304ac 100644
--- a/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout_2.ll
+++ b/polly/test/ScheduleOptimizer/mat_mul_pattern_data_layout_2.ll
@@ -20,60 +20,59 @@
 ; CHECK-NEXT:              Stmt_bb9(32 * c0 + c2, 32 * c1 + c3);
 ; CHECK-NEXT:        }
 ; CHECK-NEXT:      // 1st level tiling - Tiles
-; CHECK-NEXT:      for (int c0 = 0; c0 <= 65; c0 += 1)
-; CHECK-NEXT:        for (int c1 = 0; c1 <= 3; c1 += 1) {
-; CHECK-NEXT:          for (int c3 = 16 * c0; c3 <= 16 * c0 + 15; c3 += 1)
-; CHECK-NEXT:            for (int c4 = 256 * c1; c4 <= min(1022, 256 * c1 + 255); c4 += 1)
-; CHECK-NEXT:              CopyStmt_0(0, c3, c4);
-; CHECK-NEXT:          for (int c2 = 0; c2 <= 10; c2 += 1) {
-; CHECK-NEXT:            for (int c3 = 96 * c2; c3 <= 96 * c2 + 95; c3 += 1)
-; CHECK-NEXT:              for (int c5 = 256 * c1; c5 <= min(1022, 256 * c1 + 255); c5 += 1)
-; CHECK-NEXT:                CopyStmt_1(c3, 0, c5);
-; CHECK-NEXT:            // 1st level tiling - Points
-; CHECK-NEXT:            // Register tiling - Tiles
-; CHECK-NEXT:            for (int c3 = 0; c3 <= 1; c3 += 1)
-; CHECK-NEXT:              for (int c4 = 0; c4 <= 23; c4 += 1)
-; CHECK-NEXT:                for (int c5 = 0; c5 <= min(255, -256 * c1 + 1022); c5 += 1) {
-; CHECK-NEXT:                  // Register tiling - Points
-; CHECK-NEXT:                  // 1st level tiling - Tiles
-; CHECK-NEXT:                  // 1st level tiling - Points
-; CHECK-NEXT:                  {
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; CHECK-NEXT:                    Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; CHECK-NEXT:                  }
+; CHECK-NEXT:      for (int c1 = 0; c1 <= 3; c1 += 1) {
+; CHECK-NEXT:        for (int c3 = 0; c3 <= 1055; c3 += 1)
+; CHECK-NEXT:          for (int c4 = 256 * c1; c4 <= min(1022, 256 * c1 + 255); c4 += 1)
+; CHECK-NEXT:            CopyStmt_0(0, c3, c4);
+; CHECK-NEXT:        for (int c2 = 0; c2 <= 10; c2 += 1) {
+; CHECK-NEXT:          for (int c3 = 96 * c2; c3 <= 96 * c2 + 95; c3 += 1)
+; CHECK-NEXT:            for (int c5 = 256 * c1; c5 <= min(1022, 256 * c1 + 255); c5 += 1)
+; CHECK-NEXT:              CopyStmt_1(c3, 0, c5);
+; CHECK-NEXT:          // 1st level tiling - Points
+; CHECK-NEXT:          // Register tiling - Tiles
+; CHECK-NEXT:          for (int c3 = 0; c3 <= 131; c3 += 1)
+; CHECK-NEXT:            for (int c4 = 0; c4 <= 23; c4 += 1)
+; CHECK-NEXT:              for (int c5 = 0; c5 <= min(255, -256 * c1 + 1022); c5 += 1) {
+; CHECK-NEXT:                // Register tiling - Points
+; CHECK-NEXT:                // 1st level tiling - Tiles
+; CHECK-NEXT:                // 1st level tiling - Points
+; CHECK-NEXT:                {
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 1, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 2, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 4, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 5, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 6, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4, 8 * c3 + 7, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 1, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 2, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 4, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 5, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 6, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 1, 8 * c3 + 7, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 1, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 2, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 4, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 5, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 6, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 2, 8 * c3 + 7, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 1, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 2, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 3, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 4, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 5, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 6, 256 * c1 + c5);
+; CHECK-NEXT:                  Stmt_Copy_0(96 * c2 + 4 * c4 + 3, 8 * c3 + 7, 256 * c1 + c5);
 ; CHECK-NEXT:                }
-; CHECK-NEXT:          }
+; CHECK-NEXT:              }
 ; CHECK-NEXT:        }
+; CHECK-NEXT:      }
 ; CHECK-NEXT:    }
 ;
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
diff --git a/polly/test/ScheduleOptimizer/pattern-matching-based-opts_3.ll b/polly/test/ScheduleOptimizer/pattern-matching-based-opts_3.ll
index f2117eba4d1..f5b99eee9b0 100644
--- a/polly/test/ScheduleOptimizer/pattern-matching-based-opts_3.ll
+++ b/polly/test/ScheduleOptimizer/pattern-matching-based-opts_3.ll
@@ -73,53 +73,52 @@
 ; EXTRACTION-OF-MACRO-KERNEL-NEXT:              Stmt_bb14(32 * c0 + c2, 32 * c1 + c3);
 ; EXTRACTION-OF-MACRO-KERNEL-NEXT:        }
 ; EXTRACTION-OF-MACRO-KERNEL-NEXT:      // 1st level tiling - Tiles
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:      for (int c0 = 0; c0 <= 65; c0 += 1)
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:        for (int c1 = 0; c1 <= 3; c1 += 1)
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:          for (int c2 = 0; c2 <= 10; c2 += 1) {
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:            // 1st level tiling - Points
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:            // Register tiling - Tiles
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:            for (int c3 = 0; c3 <= 1; c3 += 1)
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:              for (int c4 = 0; c4 <= 23; c4 += 1)
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                for (int c5 = 0; c5 <= 255; c5 += 1) {
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  // Register tiling - Points
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  // 1st level tiling - Tiles
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  // 1st level tiling - Points
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  {
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 1, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 2, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 1, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 2, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 3, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 4, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 5, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 6, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                    Stmt_bb24(96 * c2 + 4 * c4 + 3, 16 * c0 + 8 * c3 + 7, 256 * c1 + c5);
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  }
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:      for (int c1 = 0; c1 <= 3; c1 += 1)
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:        for (int c2 = 0; c2 <= 10; c2 += 1) {
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:          // 1st level tiling - Points
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:          // Register tiling - Tiles
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:          for (int c3 = 0; c3 <= 131; c3 += 1)
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:            for (int c4 = 0; c4 <= 23; c4 += 1)
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:              for (int c5 = 0; c5 <= 255; c5 += 1) {
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                // Register tiling - Points
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                // 1st level tiling - Tiles
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                // 1st level tiling - Points
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                {
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 1, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 2, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 4, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 5, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 6, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4, 8 * c3 + 7, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 1, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 2, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 4, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 5, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 6, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 1, 8 * c3 + 7, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 1, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 2, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 4, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 5, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 6, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 2, 8 * c3 + 7, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 1, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 2, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 3, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 4, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 5, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 6, 256 * c1 + c5);
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:                  Stmt_bb24(96 * c2 + 4 * c4 + 3, 8 * c3 + 7, 256 * c1 + c5);
 ; EXTRACTION-OF-MACRO-KERNEL-NEXT:                }
-; EXTRACTION-OF-MACRO-KERNEL-NEXT:          }
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:              }
+; EXTRACTION-OF-MACRO-KERNEL-NEXT:        }
 ; EXTRACTION-OF-MACRO-KERNEL-NEXT:    }
 ;
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"