diff options
| -rw-r--r-- | llvm/lib/Target/X86/X86Subtarget.h | 7 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/fma-commute-x86.ll | 2 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/fma_patterns.ll | 2 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/fma_patterns_wide.ll | 2 |
4 files changed, 7 insertions, 6 deletions
diff --git a/llvm/lib/Target/X86/X86Subtarget.h b/llvm/lib/Target/X86/X86Subtarget.h index 425bc2482e9..eb0199aecbe 100644 --- a/llvm/lib/Target/X86/X86Subtarget.h +++ b/llvm/lib/Target/X86/X86Subtarget.h @@ -354,9 +354,10 @@ public: bool hasXSAVEC() const { return HasXSAVEC; } bool hasXSAVES() const { return HasXSAVES; } bool hasPCLMUL() const { return HasPCLMUL; } - bool hasFMA() const { return HasFMA; } - // FIXME: Favor FMA when both are enabled. Is this the right thing to do? - bool hasFMA4() const { return HasFMA4 && !HasFMA; } + // Prefer FMA4 to FMA - its better for commutation/memory folding and + // has equal or better performance on all supported targets. + bool hasFMA() const { return HasFMA && !HasFMA4; } + bool hasFMA4() const { return HasFMA4; } bool hasXOP() const { return HasXOP; } bool hasTBM() const { return HasTBM; } bool hasMOVBE() const { return HasMOVBE; } diff --git a/llvm/test/CodeGen/X86/fma-commute-x86.ll b/llvm/test/CodeGen/X86/fma-commute-x86.ll index 9e57b00bc0b..9a368792133 100644 --- a/llvm/test/CodeGen/X86/fma-commute-x86.ll +++ b/llvm/test/CodeGen/X86/fma-commute-x86.ll @@ -1,5 +1,5 @@ ; RUN: llc < %s -mtriple=x86_64-pc-win32 -mcpu=core-avx2 | FileCheck %s -; RUN: llc < %s -mtriple=x86_64-pc-win32 -mattr=+fma,+fma4 | FileCheck %s +; RUN: llc < %s -mtriple=x86_64-pc-win32 -mattr=+fma | FileCheck %s ; RUN: llc < %s -mcpu=bdver2 -mtriple=x86_64-pc-win32 -mattr=-fma4 | FileCheck %s attributes #0 = { nounwind } diff --git a/llvm/test/CodeGen/X86/fma_patterns.ll b/llvm/test/CodeGen/X86/fma_patterns.ll index 942d799d976..e3295e45823 100644 --- a/llvm/test/CodeGen/X86/fma_patterns.ll +++ b/llvm/test/CodeGen/X86/fma_patterns.ll @@ -1,6 +1,6 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=FMA -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4,+fma -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=FMA +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4,+fma -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=FMA4 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4 -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=FMA4 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 diff --git a/llvm/test/CodeGen/X86/fma_patterns_wide.ll b/llvm/test/CodeGen/X86/fma_patterns_wide.ll index de77a27ad2b..f412c174fe3 100644 --- a/llvm/test/CodeGen/X86/fma_patterns_wide.ll +++ b/llvm/test/CodeGen/X86/fma_patterns_wide.ll @@ -1,6 +1,6 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma -fp-contract=fast | FileCheck %s --check-prefix=FMA -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4,+fma -fp-contract=fast | FileCheck %s --check-prefix=FMA +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4,+fma -fp-contract=fast | FileCheck %s --check-prefix=FMA4 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4 -fp-contract=fast | FileCheck %s --check-prefix=FMA4 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f -fp-contract=fast | FileCheck %s --check-prefix=AVX512 |
