[RISCV][SLEEF]: Support SLEEF vector library for RISC-V target. #114014
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
llvmbot
added
llvm:ir
llvm:analysis
Member
|
@llvm/pr-subscribers-clang @llvm/pr-subscribers-llvm-analysis Author: Mark Goncharov (mga-sc) ChangesSLEEF math vector library now supports RISC-V target. This patch enables the use of auto-vectorization with Patch is 155.64 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/114014.diff 7 Files Affected:
diff --git a/llvm/include/llvm/Analysis/VecFuncs.def b/llvm/include/llvm/Analysis/VecFuncs.def
index c4586894e3e490..6d34b18de50fec 100644
--- a/llvm/include/llvm/Analysis/VecFuncs.def
+++ b/llvm/include/llvm/Analysis/VecFuncs.def
@@ -892,6 +892,155 @@ TLI_DEFINE_VECFUNC("llvm.tanh.f32", "_ZGVsMxv_tanhf", SCALABLE(4), MASKED, "_ZGV
TLI_DEFINE_VECFUNC("tgamma", "_ZGVsMxv_tgamma", SCALABLE(2), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("tgammaf", "_ZGVsMxv_tgammaf", SCALABLE(4), MASKED, "_ZGVsMxv")
+#elif defined(TLI_DEFINE_SLEEFGNUABI_SCALABLE_VECFUNCS_RISCV)
+
+TLI_DEFINE_VECFUNC("acos", "Sleef_acosdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("acosf", "Sleef_acosfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("acosh", "Sleef_acoshdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("acoshf", "Sleef_acoshfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("asin", "Sleef_asindx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("asinf", "Sleef_asinfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("asinh", "Sleef_asinhdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("asinhf", "Sleef_asinhfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("atan", "Sleef_atandx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("atanf", "Sleef_atanfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("atan2", "Sleef_atan2dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("atan2f", "Sleef_atan2fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("atanh", "Sleef_atanhdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("atanhf", "Sleef_atanhfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("cbrt", "Sleef_cbrtdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("cbrtf", "Sleef_cbrtfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("copysign", "Sleef_copysigndx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("copysignf", "Sleef_copysignfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("cos", "Sleef_cosdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("cosf", "Sleef_cosfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.cos.f64", "Sleef_cosdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.cos.f32", "Sleef_cosfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("cosh", "Sleef_coshdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("coshf", "Sleef_coshfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("cospi", "Sleef_cospidx_u05rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("cospif", "Sleef_cospifx_u05rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("erf", "Sleef_erfdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("erff", "Sleef_erffx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("erfc", "Sleef_erfcdx_u15rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("erfcf", "Sleef_erfcfx_u15rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("exp", "Sleef_expdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.exp.f64", "Sleef_expdx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("expf", "Sleef_expfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.exp.f32", "Sleef_expfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("exp10", "Sleef_exp10dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.exp10.f64", "Sleef_exp10dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("exp10f", "Sleef_exp10fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.exp10.f32", "Sleef_exp10fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("exp2", "Sleef_exp2dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("exp2f", "Sleef_exp2fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.exp2.f64", "Sleef_exp2dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.exp2.f32", "Sleef_exp2fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("expm1", "Sleef_expm1dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("expm1f", "Sleef_expm1fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("fdim", "Sleef_fdimdx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("fdimf", "Sleef_fdimfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("fma", "Sleef_fmadx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvvv")
+TLI_DEFINE_VECFUNC("fmaf", "Sleef_fmafx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvvv")
+
+TLI_DEFINE_VECFUNC("fmax", "Sleef_fmaxdx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("fmaxf", "Sleef_fmaxfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("fmin", "Sleef_fmindx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("fminf", "Sleef_fminfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("fmod", "Sleef_fmoddx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("fmodf", "Sleef_fmodfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("hypot", "Sleef_hypotdx_u05rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("hypotf", "Sleef_hypotfx_u05rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("ilogb", "Sleef_ilogbdx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("ilogbf", "Sleef_ilogbfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("ldexp", "Sleef_ldexpdx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("ldexpf", "Sleef_ldexpfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("lgamma", "Sleef_lgammadx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("lgammaf", "Sleef_lgammafx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("log", "Sleef_logdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVsMxv")
+TLI_DEFINE_VECFUNC("logf", "Sleef_logfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.log.f64", "Sleef_logdx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.log.f32", "Sleef_logfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("log10", "Sleef_log10dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.log10.f64", "Sleef_log10dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("log10f", "Sleef_log10fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.log10.f32", "Sleef_log10fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("log1p", "Sleef_log1pdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("log1pf", "Sleef_log1pfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("log2", "Sleef_log2dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("log2f", "Sleef_log2fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.log2.f64", "Sleef_log2dx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.log2.f32", "Sleef_log2fx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("modf", "Sleef_modfdx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvl8")
+TLI_DEFINE_VECFUNC("modff", "Sleef_modffx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvl4")
+
+TLI_DEFINE_VECFUNC("nextafter", "Sleef_nextafterdx_rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("nextafterf", "Sleef_nextafterfx_rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("pow", "Sleef_powdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("powf", "Sleef_powfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("llvm.pow.f64", "Sleef_powdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvv")
+TLI_DEFINE_VECFUNC("llvm.pow.f32", "Sleef_powfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvv")
+
+TLI_DEFINE_VECFUNC("sin", "Sleef_sindx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("sinf", "Sleef_sinfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.sin.f64", "Sleef_sindx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("llvm.sin.f32", "Sleef_sinfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("sincos", "Sleef_sincosdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvl8l8")
+TLI_DEFINE_VECFUNC("sincosf", "Sleef_sincosfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvl4l4")
+
+TLI_DEFINE_VECFUNC("sincospi", "Sleef_sincospidx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxvl8l8")
+TLI_DEFINE_VECFUNC("sincospif", "Sleef_sincospifx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxvl4l4")
+
+TLI_DEFINE_VECFUNC("sinh", "Sleef_sinhdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("sinhf", "Sleef_sinhfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("sinpi", "Sleef_sinpidx_u05rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("sinpif", "Sleef_sinpifx_u05rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("sqrt", "Sleef_sqrtdx_u05rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("sqrtf", "Sleef_sqrtfx_u05rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("tan", "Sleef_tandx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("tanf", "Sleef_tanfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("tanh", "Sleef_tanhdx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("tanhf", "Sleef_tanhfx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
+TLI_DEFINE_VECFUNC("tgamma", "Sleef_tgammadx_u10rvvm2", SCALABLE(2), NOMASK, "_ZGVvNxv")
+TLI_DEFINE_VECFUNC("tgammaf", "Sleef_tgammafx_u10rvvm2", SCALABLE(4), NOMASK, "_ZGVvNxv")
+
#elif defined(TLI_DEFINE_ARMPL_VECFUNCS)
TLI_DEFINE_VECFUNC("acos", "armpl_vacosq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2v")
diff --git a/llvm/include/llvm/IR/VFABIDemangler.h b/llvm/include/llvm/IR/VFABIDemangler.h
index 8450d4ce541e13..e142ae5cf84f3d 100644
--- a/llvm/include/llvm/IR/VFABIDemangler.h
+++ b/llvm/include/llvm/IR/VFABIDemangler.h
@@ -44,6 +44,7 @@ enum class VFParamKind {
enum class VFISAKind {
AdvancedSIMD, // AArch64 Advanced SIMD (NEON)
SVE, // AArch64 Scalable Vector Extension
+ RVV, // RISC-V Scalable Vector Extension
SSE, // x86 SSE
AVX, // x86 AVX
AVX2, // x86 AVX2
diff --git a/llvm/lib/Analysis/TargetLibraryInfo.cpp b/llvm/lib/Analysis/TargetLibraryInfo.cpp
index 0ee83d217a5001..65e439417fb06f 100644
--- a/llvm/lib/Analysis/TargetLibraryInfo.cpp
+++ b/llvm/lib/Analysis/TargetLibraryInfo.cpp
@@ -1322,6 +1322,14 @@ static const VecDesc VecFuncs_SLEEFGNUABI_VFScalable[] = {
#undef TLI_DEFINE_SLEEFGNUABI_SCALABLE_VECFUNCS
};
+static const VecDesc VecFuncs_SKEEFGNUABI_VFScalableRISCV[] = {
+#define TLI_DEFINE_SLEEFGNUABI_SCALABLE_VECFUNCS_RISCV
+#define TLI_DEFINE_VECFUNC(SCAL, VEC, VF, MASK, VABI_PREFIX) \
+ {SCAL, VEC, VF, MASK, VABI_PREFIX},
+#include "llvm/Analysis/VecFuncs.def"
+#undef TLI_DEFINE_SLEEFGNUABI_SCALABLE_VECFUNCS_RISCV
+};
+
static const VecDesc VecFuncs_ArmPL[] = {
#define TLI_DEFINE_ARMPL_VECFUNCS
#define TLI_DEFINE_VECFUNC(SCAL, VEC, VF, MASK, VABI_PREFIX) \
@@ -1371,6 +1379,9 @@ void TargetLibraryInfoImpl::addVectorizableFunctionsFromVecLib(
addVectorizableFunctions(VecFuncs_SLEEFGNUABI_VF4);
addVectorizableFunctions(VecFuncs_SLEEFGNUABI_VFScalable);
break;
+ case llvm::Triple::riscv64:
+ addVectorizableFunctions(VecFuncs_SKEEFGNUABI_VFScalableRISCV);
+ break;
}
break;
}
diff --git a/llvm/lib/IR/VFABIDemangler.cpp b/llvm/lib/IR/VFABIDemangler.cpp
index cdfb9fbfaa084d..2b17dccd39d5d8 100644
--- a/llvm/lib/IR/VFABIDemangler.cpp
+++ b/llvm/lib/IR/VFABIDemangler.cpp
@@ -42,6 +42,7 @@ static ParseRet tryParseISA(StringRef &MangledName, VFISAKind &ISA) {
ISA = StringSwitch<VFISAKind>(MangledName.take_front(1))
.Case("n", VFISAKind::AdvancedSIMD)
.Case("s", VFISAKind::SVE)
+ .Case("v", VFISAKind::RVV)
.Case("b", VFISAKind::SSE)
.Case("c", VFISAKind::AVX)
.Case("d", VFISAKind::AVX2)
@@ -79,9 +80,9 @@ static ParseRet tryParseVLEN(StringRef &ParseString, VFISAKind ISA,
std::pair<unsigned, bool> &ParsedVF) {
if (ParseString.consume_front("x")) {
// SVE is the only scalable ISA currently supported.
- if (ISA != VFISAKind::SVE) {
+ if (ISA != VFISAKind::SVE && ISA != VFISAKind::RVV) {
LLVM_DEBUG(dbgs() << "Vector function variant declared with scalable VF "
- << "but ISA is not SVE\n");
+ << "but ISA supported for SVE and RVV only\n");
return ParseRet::Error;
}
// We can't determine the VF of a scalable vector by looking at the vlen
@@ -301,9 +302,8 @@ static ParseRet tryParseAlign(StringRef &ParseString, Align &Alignment) {
// the number of elements of the given type which would fit in such a vector.
static std::optional<ElementCount> getElementCountForTy(const VFISAKind ISA,
const Type *Ty) {
- // Only AArch64 SVE is supported at present.
- assert(ISA == VFISAKind::SVE &&
- "Scalable VF decoding only implemented for SVE\n");
+ assert((ISA == VFISAKind::SVE || ISA == VFISAKind::RVV) &&
+ "Scalable VF decoding only implemented for SVE and RVV\n");
if (Ty->isIntegerTy(64) || Ty->isDoubleTy() || Ty->isPointerTy())
return ElementCount::getScalable(2);
diff --git a/llvm/test/CodeGen/RISCV/replace-with-veclib-sleef-scalable.ll b/llvm/test/CodeGen/RISCV/replace-with-veclib-sleef-scalable.ll
new file mode 100644
index 00000000000000..5bfe345ae8b9cc
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/replace-with-veclib-sleef-scalable.ll
@@ -0,0 +1,492 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 4
+; RUN: opt -mtriple=riscv64-unknown-linux-gnu -mattr=+v -vector-library=sleefgnuabi -replace-with-veclib -S < %s | FileCheck %s
+
+;.
+; CHECK: @llvm.compiler.used = appending global [16 x ptr] [ptr @Sleef_cosdx_u10rvvm2, ptr @Sleef_cosfx_u10rvvm2, ptr @Sleef_expfx_u10rvvm2, ptr @Sleef_exp10dx_u10rvvm2, ptr @Sleef_exp10fx_u10rvvm2, ptr @Sleef_exp2dx_u10rvvm2, ptr @Sleef_exp2fx_u10rvvm2, ptr @Sleef_logfx_u10rvvm2, ptr @Sleef_log10dx_u10rvvm2, ptr @Sleef_log10fx_u10rvvm2, ptr @Sleef_log2dx_u10rvvm2, ptr @Sleef_log2fx_u10rvvm2, ptr @Sleef_sindx_u10rvvm2, ptr @Sleef_sinfx_u10rvvm2, ptr @Sleef_fmindx_rvvm2, ptr @Sleef_fminfx_rvvm2], section "llvm.metadata"
+;.
+define <vscale x 2 x double> @llvm_ceil_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: define <vscale x 2 x double> @llvm_ceil_vscale_f64(
+; CHECK-SAME: <vscale x 2 x double> [[IN:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> [[IN]])
+; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+;
+ %1 = call fast <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> %in)
+ ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_ceil_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: define <vscale x 4 x float> @llvm_ceil_vscale_f32(
+; CHECK-SAME: <vscale x 4 x float> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> [[IN]])
+; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+;
+ %1 = call fast <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> %in)
+ ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_copysign_vscale_f64(<vscale x 2 x double> %mag, <vscale x 2 x double> %sgn) {
+; CHECK-LABEL: define <vscale x 2 x double> @llvm_copysign_vscale_f64(
+; CHECK-SAME: <vscale x 2 x double> [[MAG:%.*]], <vscale x 2 x double> [[SGN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> [[MAG]], <vscale x 2 x double> [[SGN]])
+; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+;
+ %1 = call fast <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> %mag, <vscale x 2 x double> %sgn)
+ ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_copysign_vscale_f32(<vscale x 4 x float> %mag, <vscale x 4 x float> %sgn) {
+; CHECK-LABEL: define <vscale x 4 x float> @llvm_copysign_vscale_f32(
+; CHECK-SAME: <vscale x 4 x float> [[MAG:%.*]], <vscale x 4 x float> [[SGN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> [[MAG]], <vscale x 4 x float> [[SGN]])
+; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+;
+ %1 = call fast <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> %mag, <vscale x 4 x float> %sgn)
+ ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_cos_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: define <vscale x 2 x double> @llvm_cos_vscale_f64(
+; CHECK-SAME: <vscale x 2 x double> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @Sleef_cosdx_u10rvvm2(<vscale x 2 x double> [[IN]])
+; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+;
+ %1 = call fast <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> %in)
+ ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_cos_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: define <vscale x 4 x float> @llvm_cos_vscale_f32(
+; CHECK-SAME: <vscale x 4 x float> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @Sleef_cosfx_u10rvvm2(<vscale x 4 x float> [[IN]])
+; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+;
+ %1 = call fast <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %in)
+ ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_exp_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: define <vscale x 2 x double> @llvm_exp_vscale_f64(
+; CHECK-SAME: <vscale x 2 x double> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> [[IN]])
+; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+;
+ %1 = call fast <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> %in)
+ ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_exp_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: define <vscale x 4 x float> @llvm_exp_vscale_f32(
+; CHECK-SAME: <vscale x 4 x float> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @Sleef_expfx_u10rvvm2(<vscale x 4 x float> [[IN]])
+; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+;
+ %1 = call fast <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %in)
+ ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_exp10_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: define <vscale x 2 x double> @llvm_exp10_vscale_f64(
+; CHECK-SAME: <vscale x 2 x double> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @Sleef_exp10dx_u10rvvm2(<vscale x 2 x double> [[IN]])
+; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
+;
+ %1 = call fast <vscale x 2 x double> @llvm.exp10.nxv2f64(<vscale x 2 x double> %in)
+ ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_exp10_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: define <vscale x 4 x float> @llvm_exp10_vscale_f32(
+; CHECK-SAME: <vscale x 4 x float> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @Sleef_exp10fx_u10rvvm2(<vscale x 4 x float> [[IN]])
+; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
+;
+ %1 = call fast <vscale x 4 x float> @llvm.exp10.nxv4f32(<vscale x 4 x float> %in)
+ ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_exp2_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: define <vscale x 2 x double> @llvm_exp2_vscale_f64(
+; CHECK-SAME: <vscale x 2 x double> [[IN:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @Sleef_exp2dx_u10rvvm2(<vscale x 2 x double...
[truncated]
|
mag-mga
force-pushed
the
mga-sc/riscv-sleef
branch
from
529fde0 to
cb999c1
Compare
topperc
reviewed
Oct 29, 2024
topperc
reviewed
Oct 29, 2024
Collaborator
There was a problem hiding this comment.
Where does the "u10" and "u05" etc come from. I don't see that in the name of the SVE SLEEF functions.
Contributor
Author
There was a problem hiding this comment.
Yes, ARM replaces vector functions using format "ABI_name". For this purpose, they create GNUABI support in SLEEF for AArch64 only - (look at sleef.org support Francesco Petrogalli and llvm aarch64 sleef support)
Actually, SLEEF has own function naming.
- from funcproto.h we has info about possible precision and type.
- from CMakeLists.txt we set info about mangling name for specific architecture
- finally, mkrename.c use this info and in runtime rename functions.
I made the names match as in SLEEF library.
farzonl
reviewed
Nov 6, 2024
Member
There was a problem hiding this comment.
for all these trig definitions don't forget to also include the llvm intrinsics for llvm.acos, llvm.atan, llvm.atan2, llvm.asin, llvm.cosh, llvm.tanh, & , llvm.sinH
mag-mga
force-pushed
the
mga-sc/riscv-sleef
branch
from
1da2a96 to
3b9f052
Compare
topperc
reviewed
Nov 6, 2024
mag-mga
force-pushed
the
mga-sc/riscv-sleef
branch
from
3b9f052 to
ae87d0d
Compare
topperc
reviewed
Nov 7, 2024
topperc
reviewed
Nov 7, 2024
topperc
reviewed
Nov 7, 2024
mag-mga
force-pushed
the
mga-sc/riscv-sleef
branch
from
ae87d0d to
096ed92
Compare
Member
|
@mga-sc I'm trying to run some experiments with your PR and will post as soon as they are done, but can I ask you to add the following code to your PR? So that clang can accept -fveclib=SLEEF when building for riscv64 |
llvmbot
added
clang
Contributor
Author
Add clang support. Also add test to fveclib.c to check. |
SLEEF math vector library support RISC-V target. Commit: shibatch/sleef#477 This patch enables the use of auto-vectorization with subsequent replacement by the corresponding SLEEF function.
mag-mga
force-pushed
the
mga-sc/riscv-sleef
branch
from
a187cce to
5ec5bac
Compare
Contributor
Author
|
@mikhailramalho , @topperc , ping |
Contributor
Author
|
I can't merge this PR. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
SLEEF math vector library now supports RISC-V target.
Commit: shibatch/sleef#477
This patch enables the use of auto-vectorization with
subsequent replacement by the corresponding SLEEF function.