Author: Paschalis Mpeis Date: 2023-11-28T12:02:12Z New Revision: 6f797921e23fe9a4500222e69ebd75aa7ba53ec1
URL: https://github.com/llvm/llvm-project/commit/6f797921e23fe9a4500222e69ebd75aa7ba53ec1 DIFF: https://github.com/llvm/llvm-project/commit/6f797921e23fe9a4500222e69ebd75aa7ba53ec1.diff LOG: [TLI] Pass replace-with-veclib works with Scalable Vectors. The pass uses the Masked variant of TLI method when the Intrinsic operates on Scalable Vectors and it fails to find a non-Masked variant. Added: Modified: llvm/lib/Analysis/VFABIDemangling.cpp llvm/lib/CodeGen/ReplaceWithVeclib.cpp llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-armpl.ll llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll Removed: ################################################################################ diff --git a/llvm/lib/Analysis/VFABIDemangling.cpp b/llvm/lib/Analysis/VFABIDemangling.cpp index 88f61cfeb9ba4e5..85880257a320860 100644 --- a/llvm/lib/Analysis/VFABIDemangling.cpp +++ b/llvm/lib/Analysis/VFABIDemangling.cpp @@ -126,7 +126,7 @@ static ParseRet tryParseLinearTokenWithRuntimeStep(StringRef &ParseString, return ParseRet::None; } -/// The function looks for the following stringt at the beginning of +/// The function looks for the following string at the beginning of /// the input string `ParseString`: /// /// <token> <number> diff --git a/llvm/lib/CodeGen/ReplaceWithVeclib.cpp b/llvm/lib/CodeGen/ReplaceWithVeclib.cpp index 36c91b7fa97e462..d31a793556dfded 100644 --- a/llvm/lib/CodeGen/ReplaceWithVeclib.cpp +++ b/llvm/lib/CodeGen/ReplaceWithVeclib.cpp @@ -105,6 +105,7 @@ static bool replaceWithCallToVeclib(const TargetLibraryInfo &TLI, // all vector operands have identical vector width. ElementCount VF = ElementCount::getFixed(0); SmallVector<Type *> ScalarTypes; + bool MayBeMasked = false; for (auto Arg : enumerate(CI.args())) { auto *ArgType = Arg.value()->getType(); // Vector calls to intrinsics can still have @@ -121,17 +122,13 @@ static bool replaceWithCallToVeclib(const TargetLibraryInfo &TLI, return false; } ElementCount NumElements = VectorArgTy->getElementCount(); - if (NumElements.isScalable()) { - // The current implementation does not support - // scalable vectors. - return false; - } - if (VF.isNonZero() && VF != NumElements) { - // The diff erent arguments diff er in vector size. + if (NumElements.isScalable()) + MayBeMasked = true; + + // The diff erent arguments diff er in vector size. + if (VF.isNonZero() && VF != NumElements) return false; - } else { - VF = NumElements; - } + VF = NumElements; ScalarTypes.push_back(VectorArgTy->getElementType()); } } @@ -152,11 +149,14 @@ static bool replaceWithCallToVeclib(const TargetLibraryInfo &TLI, return false; } + // Assume it has a mask when that is a possibility and has no mapping for + // a Non-Masked variant. + const bool IsMasked = + MayBeMasked && !TLI.getVectorMappingInfo(ScalarName, VF, false); // Try to find the mapping for the scalar version of this intrinsic // and the exact vector width of the call operands in the // TargetLibraryInfo. - StringRef TLIName = TLI.getVectorizedFunction(ScalarName, VF); - + StringRef TLIName = TLI.getVectorizedFunction(ScalarName, VF, IsMasked); LLVM_DEBUG(dbgs() << DEBUG_TYPE << ": Looking up TLI mapping for `" << ScalarName << "` and vector width " << VF << ".\n"); diff --git a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-armpl.ll b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-armpl.ll index 18431ae021f9766..633cb220f52464c 100644 --- a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-armpl.ll +++ b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-armpl.ll @@ -15,7 +15,7 @@ declare <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double>) declare <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float>) ;. -; CHECK: @llvm.compiler.used = appending global [16 x ptr] [ptr @armpl_vcosq_f64, ptr @armpl_vcosq_f32, ptr @armpl_vsinq_f64, ptr @armpl_vsinq_f32, ptr @armpl_vexpq_f64, ptr @armpl_vexpq_f32, ptr @armpl_vexp2q_f64, ptr @armpl_vexp2q_f32, ptr @armpl_vexp10q_f64, ptr @armpl_vexp10q_f32, ptr @armpl_vlogq_f64, ptr @armpl_vlogq_f32, ptr @armpl_vlog2q_f64, ptr @armpl_vlog2q_f32, ptr @armpl_vlog10q_f64, ptr @armpl_vlog10q_f32], section "llvm.metadata" +; CHECK: @llvm.compiler.used = appending global [32 x ptr] [ptr @armpl_vcosq_f64, ptr @armpl_vcosq_f32, ptr @armpl_svcos_f64_x, ptr @armpl_svcos_f32_x, ptr @armpl_vsinq_f64, ptr @armpl_vsinq_f32, ptr @armpl_svsin_f64_x, ptr @armpl_svsin_f32_x, ptr @armpl_vexpq_f64, ptr @armpl_vexpq_f32, ptr @armpl_svexp_f64_x, ptr @armpl_svexp_f32_x, ptr @armpl_vexp2q_f64, ptr @armpl_vexp2q_f32, ptr @armpl_svexp2_f64_x, ptr @armpl_svexp2_f32_x, ptr @armpl_vexp10q_f64, ptr @armpl_vexp10q_f32, ptr @armpl_svexp10_f64_x, ptr @armpl_svexp10_f32_x, ptr @armpl_vlogq_f64, ptr @armpl_vlogq_f32, ptr @armpl_svlog_f64_x, ptr @armpl_svlog_f32_x, ptr @armpl_vlog2q_f64, ptr @armpl_vlog2q_f32, ptr @armpl_svlog2_f64_x, ptr @armpl_svlog2_f32_x, ptr @armpl_vlog10q_f64, ptr @armpl_vlog10q_f32, ptr @armpl_svlog10_f64_x, ptr @armpl_svlog10_f32_x], section "llvm.metadata" ;. define <2 x double> @llvm_cos_f64(<2 x double> %in) { ; CHECK-LABEL: define <2 x double> @llvm_cos_f64 @@ -40,7 +40,7 @@ define <4 x float> @llvm_cos_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_cos_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_cos_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1:[0-9]+]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svcos_f64_x(<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) @@ -50,7 +50,7 @@ define <vscale x 2 x double> @llvm_cos_vscale_f64(<vscale x 2 x double> %in) #0 define <vscale x 4 x float> @llvm_cos_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_cos_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svcos_f32_x(<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) @@ -85,7 +85,7 @@ define <4 x float> @llvm_sin_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_sin_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_sin_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svsin_f64_x(<vscale x 2 x double> [[IN]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> %in) @@ -95,7 +95,7 @@ define <vscale x 2 x double> @llvm_sin_vscale_f64(<vscale x 2 x double> %in) #0 define <vscale x 4 x float> @llvm_sin_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_sin_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svsin_f32_x(<vscale x 4 x float> [[IN]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %in) @@ -130,7 +130,7 @@ define <4 x float> @llvm_exp_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_exp_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_exp_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svexp_f64_x(<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) @@ -140,7 +140,7 @@ define <vscale x 2 x double> @llvm_exp_vscale_f64(<vscale x 2 x double> %in) #0 define <vscale x 4 x float> @llvm_exp_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_exp_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svexp_f32_x(<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) @@ -175,7 +175,7 @@ define <4 x float> @llvm_exp2_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_exp2_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_exp2_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svexp2_f64_x(<vscale x 2 x double> [[IN]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> %in) @@ -185,7 +185,7 @@ define <vscale x 2 x double> @llvm_exp2_vscale_f64(<vscale x 2 x double> %in) #0 define <vscale x 4 x float> @llvm_exp2_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_exp2_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svexp2_f32_x(<vscale x 4 x float> [[IN]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %in) @@ -220,7 +220,7 @@ define <4 x float> @llvm_exp10_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_exp10_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_exp10_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp10.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svexp10_f64_x(<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) @@ -230,7 +230,7 @@ define <vscale x 2 x double> @llvm_exp10_vscale_f64(<vscale x 2 x double> %in) # define <vscale x 4 x float> @llvm_exp10_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_exp10_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp10.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svexp10_f32_x(<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) @@ -265,7 +265,7 @@ define <4 x float> @llvm_log_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_log_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_log_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svlog_f64_x(<vscale x 2 x double> [[IN]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> %in) @@ -275,7 +275,7 @@ define <vscale x 2 x double> @llvm_log_vscale_f64(<vscale x 2 x double> %in) #0 define <vscale x 4 x float> @llvm_log_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_log_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svlog_f32_x(<vscale x 4 x float> [[IN]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %in) @@ -310,7 +310,7 @@ define <4 x float> @llvm_log2_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_log2_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_log2_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svlog2_f64_x(<vscale x 2 x double> [[IN]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> %in) @@ -320,7 +320,7 @@ define <vscale x 2 x double> @llvm_log2_vscale_f64(<vscale x 2 x double> %in) #0 define <vscale x 4 x float> @llvm_log2_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_log2_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svlog2_f32_x(<vscale x 4 x float> [[IN]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %in) @@ -355,7 +355,7 @@ define <4 x float> @llvm_log10_f32(<4 x float> %in) { define <vscale x 2 x double> @llvm_log10_vscale_f64(<vscale x 2 x double> %in) #0 { ; CHECK-LABEL: define <vscale x 2 x double> @llvm_log10_vscale_f64 ; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @armpl_svlog10_f64_x(<vscale x 2 x double> [[IN]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> %in) @@ -365,7 +365,7 @@ define <vscale x 2 x double> @llvm_log10_vscale_f64(<vscale x 2 x double> %in) # define <vscale x 4 x float> @llvm_log10_vscale_f32(<vscale x 4 x float> %in) #0 { ; CHECK-LABEL: define <vscale x 4 x float> @llvm_log10_vscale_f32 ; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) #[[ATTR1]] { -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> [[IN]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @armpl_svlog10_f32_x(<vscale x 4 x float> [[IN]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %in) @@ -380,7 +380,7 @@ declare <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float>, <vscale x 4 ; ; There is a bug in the replace-with-veclib pass, and for intrinsics which take ; more than one arguments, but has just one overloaded type, it incorrectly -; reconstructs the scalar name, for pow specificlly it is searching for: +; reconstructs the scalar name, for pow specifically it is searching for: ; llvm.pow.f64.f64 and llvm.pow.f32.f32 ; diff --git a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll index 8b06c41bcb1a6d1..969945590a0a184 100644 --- a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll +++ b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll @@ -5,6 +5,9 @@ target triple = "aarch64-unknown-linux-gnu" ; NOTE: The existing TLI mappings are not used since the -replace-with-veclib pass is broken for scalable vectors. +;. +; CHECK: @llvm.compiler.used = appending global [16 x ptr] [ptr @_ZGVsMxv_cos, ptr @_ZGVsMxv_cosf, ptr @_ZGVsMxv_exp, ptr @_ZGVsMxv_expf, ptr @_ZGVsMxv_exp2, ptr @_ZGVsMxv_exp2f, ptr @_ZGVsMxv_exp10, ptr @_ZGVsMxv_exp10f, ptr @_ZGVsMxv_log, ptr @_ZGVsMxv_logf, ptr @_ZGVsMxv_log10, ptr @_ZGVsMxv_log10f, ptr @_ZGVsMxv_log2, ptr @_ZGVsMxv_log2f, ptr @_ZGVsMxv_sin, ptr @_ZGVsMxv_sinf], section "llvm.metadata" +;. define <vscale x 2 x double> @llvm_ceil_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_ceil_vscale_f64( ; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) @@ -43,7 +46,7 @@ define <vscale x 4 x float> @llvm_copysign_vscale_f32(<vscale x 4 x float> %mag, define <vscale x 2 x double> @llvm_cos_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_cos_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_cos(<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) @@ -52,7 +55,7 @@ define <vscale x 2 x double> @llvm_cos_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_cos_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_cos_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_cosf(<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) @@ -61,7 +64,7 @@ define <vscale x 4 x float> @llvm_cos_vscale_f32(<vscale x 4 x float> %in) { define <vscale x 2 x double> @llvm_exp_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_exp_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_exp(<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) @@ -70,7 +73,7 @@ define <vscale x 2 x double> @llvm_exp_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_exp_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_exp_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_expf(<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) @@ -79,7 +82,7 @@ define <vscale x 4 x float> @llvm_exp_vscale_f32(<vscale x 4 x float> %in) { define <vscale x 2 x double> @llvm_exp2_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_exp2_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_exp2(<vscale x 2 x double> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> %in) @@ -88,7 +91,7 @@ define <vscale x 2 x double> @llvm_exp2_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_exp2_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_exp2_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_exp2f(<vscale x 4 x float> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %in) @@ -97,7 +100,7 @@ define <vscale x 4 x float> @llvm_exp2_vscale_f32(<vscale x 4 x float> %in) { define <vscale x 2 x double> @llvm_exp10_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_exp10_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp10.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_exp10(<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) @@ -106,7 +109,7 @@ define <vscale x 2 x double> @llvm_exp10_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_exp10_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_exp10_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp10.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_exp10f(<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) @@ -169,7 +172,7 @@ define <vscale x 4 x float> @llvm_fma_vscale_f32(<vscale x 4 x float> %a, <vscal define <vscale x 2 x double> @llvm_log_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_log_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_log(<vscale x 2 x double> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> %in) @@ -178,7 +181,7 @@ define <vscale x 2 x double> @llvm_log_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_log_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_log_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_logf(<vscale x 4 x float> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %in) @@ -187,7 +190,7 @@ define <vscale x 4 x float> @llvm_log_vscale_f32(<vscale x 4 x float> %in) { define <vscale x 2 x double> @llvm_log10_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_log10_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_log10(<vscale x 2 x double> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> %in) @@ -196,7 +199,7 @@ define <vscale x 2 x double> @llvm_log10_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_log10_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_log10_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_log10f(<vscale x 4 x float> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %in) @@ -205,7 +208,7 @@ define <vscale x 4 x float> @llvm_log10_vscale_f32(<vscale x 4 x float> %in) { define <vscale x 2 x double> @llvm_log2_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_log2_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_log2(<vscale x 2 x double> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> %in) @@ -214,7 +217,7 @@ define <vscale x 2 x double> @llvm_log2_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_log2_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_log2_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_log2f(<vscale x 4 x float> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %in) @@ -331,7 +334,7 @@ define <vscale x 4 x float> @llvm_round_vscale_f32(<vscale x 4 x float> %in) { define <vscale x 2 x double> @llvm_sin_vscale_f64(<vscale x 2 x double> %in) { ; CHECK-LABEL: @llvm_sin_vscale_f64( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 2 x double> @_ZGVsMxv_sin(<vscale x 2 x double> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]] ; %1 = call fast <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> %in) @@ -340,7 +343,7 @@ define <vscale x 2 x double> @llvm_sin_vscale_f64(<vscale x 2 x double> %in) { define <vscale x 4 x float> @llvm_sin_vscale_f32(<vscale x 4 x float> %in) { ; CHECK-LABEL: @llvm_sin_vscale_f32( -; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> [[IN:%.*]]) +; CHECK-NEXT: [[TMP1:%.*]] = call fast <vscale x 4 x float> @_ZGVsMxv_sinf(<vscale x 4 x float> [[IN:%.*]]) ; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]] ; %1 = call fast <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %in) _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
