diff options
| author |  Benoit Jacob <benoitjacob@google.com> | 2015-01-31 14:15:57 -0500 |
|---|---|---|
| committer | Benoit Jacob <benoitjacob@google.com> | 2015-01-31 14:15:57 -0500 |
| commit | 340b8afb14bb06788570ba22ba4ccba674402f09 (patch) | |
| tree | 33cd52e2ad9f5d1f5f56044fb4cbaa5a97ca98a5 /Eigen/src/Core/arch/AltiVec/PacketMath.h | |
| parent | 9f99f61e69a70e0a209d5f93e78a9257685cd70d (diff) | |
bug #936, patch 1.5/3: rename _FUSED_ macros to _SINGLE_INSTRUCTION_,
because this is what they are about. "Fused" means "no intermediate rounding
between the mul and the add, only one rounding at the end". Instead,
what we are concerned about here is whether a temporary register is needed,
i.e. whether the MUL and ADD are separate instructions.
Concretely, on ARM NEON, a single-instruction mul-add is always available: VMLA.
But a true fused mul-add is only available on VFPv4: VFMA.
Diffstat (limited to 'Eigen/src/Core/arch/AltiVec/PacketMath.h')
| -rwxr-xr-x | Eigen/src/Core/arch/AltiVec/PacketMath.h | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/Eigen/src/Core/arch/AltiVec/PacketMath.h b/Eigen/src/Core/arch/AltiVec/PacketMath.h index 27df5a025..578b303a0 100755 --- a/Eigen/src/Core/arch/AltiVec/PacketMath.h +++ b/Eigen/src/Core/arch/AltiVec/PacketMath.h @@ -18,12 +18,12 @@ namespace internal { #define EIGEN_CACHEFRIENDLY_PRODUCT_THRESHOLD 4 #endif -#ifndef EIGEN_HAS_FUSED_MADD -#define EIGEN_HAS_FUSED_MADD 1 +#ifndef EIGEN_HAS_SINGLE_INSTRUCTION_MADD +#define EIGEN_HAS_SINGLE_INSTRUCTION_MADD 1 #endif -#ifndef EIGEN_HAS_FUSED_CJMADD -#define EIGEN_HAS_FUSED_CJMADD +#ifndef EIGEN_HAS_SINGLE_INSTRUCTION_CJMADD +#define EIGEN_HAS_SINGLE_INSTRUCTION_CJMADD #endif // NOTE Altivec has 32 registers, but Eigen only accepts a value of 8 or 16 |