test case for Aggressive FMA on AArch64

[steleman]

Summary

This test case demonstrates(?) the effects of enabling Aggressive FMA on AArch64.

For now it is limited to Cavium ThunderX2 T99.

SingleSource/UnitTests/AggressiveFMA/AArch64/CMakeLists.txt

+list(APPEND CFLAGS -O2 -std=c99 -mcpu=thunderx2t99)
+list(APPEND CFLAGS -funroll-loops -ffast-math)
+list(APPEND CFLAGS -Xclang -menable-unsafe-fp-math)
+llvm_singlesource()

SingleSource/UnitTests/AggressiveFMA/AArch64/Makefile

+# SingleSource/UnitTests/AggressiveFMA/AArch64/Makefile
+
+DIRS =
+LEVEL = ../../../..
+
+include $(LEVEL)/SingleSource/Makefile.singlesrc
+
+CFLAGS += -O2 -std=c99 -mcpu=thunderx2t99 -march=armv8.1-a+lse
+CFLAGS += -funroll-loops -ffast-math -Xclang -menable-unsafe-fp-math
+

SingleSource/UnitTests/AggressiveFMA/AArch64/aarch64_aggressive_fma.c

+/* This test program demonstrates the effects of enabling aggressive FMA
+ * on AArch64. With aggressive FMA enabled, CodeGen will fuse instructions
+ * for SDValues with one or more use. With aggressive FMA disabled, this
+ * fusion does not happen.
+ */
+
+/* clang -O2 -std=c99 -Wall -mcpu=thunderx2t99 -march=armv8.1-a+lse
+ * -funroll-loops -ffast-math -Xclang -menable-unsafe-fp-math
+ * -emit-llvm -S fma.c -o fma.ll
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <math.h>
+
+static const double AE[] = { -0.00, 0.00, 0.00, 0.00, 0.00, 0.00,
+                             0.00, 0.00, 0.00, 0.00 };
+
+static const double BE[] = { 1102499.00, -2.00, -3.00, -4.00, -5.00,
+                             -6.00, -7.00, -8.00, -9.00, -10.00 };
+
+double reset(double x, double y)
+{
+  double i;
+  if (modf(x, &i) == 0.0)
+    return x + y;
+
+  return x - y;
+}
+
+int main(int argc, char* argv[])
+{
+  int z;
+  if (argc >= 2)
+    z = atoi(argv[1]);
+  else
+    z = 10;
+
+  double a = 3.0;
+  double b = 5.0;
+  double c = 10.0;
+  (void) fprintf(stderr, "a=%lf b=%lf c=%lf\n", a, b, c);
+
+  for (int i = 0; i < z; ++i) {
+    double x = (double) i;
+    double p1 = 1.0;
+    double n1 = -1.0;
+    double y;
+
+    if ((i % 2) == 0)
+      y = p1;
+    else
+      y = n1;
+
+    a *= y + p1 + a;
+    a *= y + ((c + a) * 2.0) - (a + y + x);
+    a -= n1 * (y * a);
+
+    (void) fprintf(stderr, "a=%lf b=%lf c=%lf\n", a, b, c);
+
+    if ((i % 2) == 0)
+      b = p1 - ((n1 + a) * (a - n1));
+    else
+      b = p1 + ((n1 - a) * (a - n1));
+
+    a *= (p1 - a) * x;
+    b -= reset(x, b - y + (a + b));
+
+    (void) fprintf(stderr, "a=%lf b=%lf c=%lf", a, b, c);
+    if ((a == AE[i]) && (b == BE[i]))
+      (void) fprintf(stderr, " -----> PASS.");
+    else {
+      (void) fprintf(stderr, " -----> FAIL: ");
+      if (a != AE[i])
+        (void) fprintf(stderr, "(a == %lf, expected %lf)", a, AE[i]);
+      else if (b != BE[i])
+        (void) fprintf(stderr, "(b == %lf, expected %lf)", b, BE[i]);
+    }
+
+    (void) fprintf(stderr, "\n\n");
+  }
+
+  return 0;
+}
+
+

SingleSource/UnitTests/AggressiveFMA/AArch64/aarch64_aggressive_fma.reference_output

+a=3.000000 b=5.000000 c=10.000000
+a=1050.000000 b=5.000000 c=10.000000
+a=0.000000 b=1102499.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=1102499.000000 c=10.000000
+a=0.000000 b=-2.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-2.000000 c=10.000000
+a=0.000000 b=-3.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-3.000000 c=10.000000
+a=0.000000 b=-4.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-4.000000 c=10.000000
+a=0.000000 b=-5.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-5.000000 c=10.000000
+a=0.000000 b=-6.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-6.000000 c=10.000000
+a=0.000000 b=-7.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-7.000000 c=10.000000
+a=0.000000 b=-8.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-8.000000 c=10.000000
+a=0.000000 b=-9.000000 c=10.000000 -----> PASS.
+
+a=0.000000 b=-9.000000 c=10.000000
+a=0.000000 b=-10.000000 c=10.000000 -----> PASS.
+
+exit 0

SingleSource/UnitTests/AggressiveFMA/CMakeLists.txt

+if(ARCH STREQUAL "AArch64")
+  add_subdirectory(AArch64)
+endif()
+
+llvm_singlesource(PREFIX "AggessiveFMA-")

SingleSource/UnitTests/CMakeLists.txt

+add_subdirectory(AggressiveFMA)
 add_subdirectory(C++11)
 add_subdirectory(SignlessTypes)
 add_subdirectory(Threads)

SingleSource/UnitTests/Makefile

 # FIXME: Disable SJLJ tests for now, until EH edges are represented.
 DIRS :=
 
+DIRS += AggressiveFMA
 DIRS += Vector
 DIRS += Vectorizer