[llvm] r361401 - [IR] allow fast-math-flags on select of FP values
Sanjay Patel via llvm-commits
llvm-commits at lists.llvm.org
Wed May 22 08:50:47 PDT 2019
Author: spatel
Date: Wed May 22 08:50:46 2019
New Revision: 361401
URL: http://llvm.org/viewvc/llvm-project?rev=361401&view=rev
Log:
[IR] allow fast-math-flags on select of FP values
This is a minimal start to correcting a problem most directly discussed in PR38086:
https://bugs.llvm.org/show_bug.cgi?id=38086
We have been hacking around a limitation for FP select patterns by using the
fast-math-flags on the condition of the select rather than the select itself.
This patch just allows FMF to appear with the 'select' opcode. No changes are
needed to "FPMathOperator" because it already includes select-of-FP because
that definition is based on the (return) value type.
Once we have this ability, we can start correcting and adding IR transforms
to use the FMF on a 'select' instruction. The instcombine and vectorizer test
diffs only show that the IRBuilder change is behaving as expected by applying
an FMF guard value to 'select'.
For reference:
rL241901 - allowed FMF with fcmp
rL255555 - allowed FMF with FP calls
Differential Revision: https://reviews.llvm.org/D61917
Modified:
llvm/trunk/docs/LangRef.rst
llvm/trunk/include/llvm/IR/IRBuilder.h
llvm/trunk/lib/AsmParser/LLParser.cpp
llvm/trunk/lib/Bitcode/Reader/BitcodeReader.cpp
llvm/trunk/lib/Bitcode/Writer/BitcodeWriter.cpp
llvm/trunk/test/Bitcode/compatibility.ll
llvm/trunk/test/CodeGen/Generic/expand-experimental-reductions.ll
llvm/trunk/test/Transforms/InstCombine/fast-math.ll
llvm/trunk/test/Transforms/InstCombine/pow-sqrt.ll
llvm/trunk/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll
llvm/trunk/test/Transforms/LoopVectorize/minmax_reduction.ll
Modified: llvm/trunk/docs/LangRef.rst
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/LangRef.rst?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/docs/LangRef.rst (original)
+++ llvm/trunk/docs/LangRef.rst Wed May 22 08:50:46 2019
@@ -9931,7 +9931,7 @@ Syntax:
::
- <result> = select selty <cond>, <ty> <val1>, <ty> <val2> ; yields ty
+ <result> = select [fast-math flags] selty <cond>, <ty> <val1>, <ty> <val2> ; yields ty
selty is either i1 or {<N x i1>}
@@ -9948,6 +9948,11 @@ The '``select``' instruction requires an
values indicating the condition, and two values of the same :ref:`first
class <t_firstclass>` type.
+#. The optional ``fast-math flags`` marker indicates that the select has one or more
+ :ref:`fast-math flags <fastmath>`. These are optimization hints to enable
+ otherwise unsafe floating-point optimizations. Fast-math flags are only valid
+ for selects that return a floating-point scalar or vector type.
+
Semantics:
""""""""""
Modified: llvm/trunk/include/llvm/IR/IRBuilder.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/IR/IRBuilder.h?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/include/llvm/IR/IRBuilder.h (original)
+++ llvm/trunk/include/llvm/IR/IRBuilder.h Wed May 22 08:50:46 2019
@@ -2067,6 +2067,8 @@ public:
MDNode *Unpred = MDFrom->getMetadata(LLVMContext::MD_unpredictable);
Sel = addBranchMetadata(Sel, Prof, Unpred);
}
+ if (isa<FPMathOperator>(Sel))
+ Sel = cast<SelectInst>(setFPAttrs(Sel, nullptr /* MDNode* */, FMF));
return Insert(Sel, Name);
}
Modified: llvm/trunk/lib/AsmParser/LLParser.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/AsmParser/LLParser.cpp?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/lib/AsmParser/LLParser.cpp (original)
+++ llvm/trunk/lib/AsmParser/LLParser.cpp Wed May 22 08:50:46 2019
@@ -5701,7 +5701,19 @@ int LLParser::ParseInstruction(Instructi
case lltok::kw_inttoptr:
case lltok::kw_ptrtoint: return ParseCast(Inst, PFS, KeywordVal);
// Other.
- case lltok::kw_select: return ParseSelect(Inst, PFS);
+ case lltok::kw_select: {
+ FastMathFlags FMF = EatFastMathFlagsIfPresent();
+ int Res = ParseSelect(Inst, PFS);
+ if (Res != 0)
+ return Res;
+ if (FMF.any()) {
+ if (!Inst->getType()->isFPOrFPVectorTy())
+ return Error(Loc, "fast-math-flags specified for select without "
+ "floating-point scalar or vector return type");
+ Inst->setFastMathFlags(FMF);
+ }
+ return 0;
+ }
case lltok::kw_va_arg: return ParseVA_Arg(Inst, PFS);
case lltok::kw_extractelement: return ParseExtractElement(Inst, PFS);
case lltok::kw_insertelement: return ParseInsertElement(Inst, PFS);
Modified: llvm/trunk/lib/Bitcode/Reader/BitcodeReader.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Bitcode/Reader/BitcodeReader.cpp?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/lib/Bitcode/Reader/BitcodeReader.cpp (original)
+++ llvm/trunk/lib/Bitcode/Reader/BitcodeReader.cpp Wed May 22 08:50:46 2019
@@ -3835,6 +3835,11 @@ Error BitcodeReader::parseFunctionBody(F
I = SelectInst::Create(Cond, TrueVal, FalseVal);
InstructionList.push_back(I);
+ if (OpNum < Record.size() && isa<FPMathOperator>(I)) {
+ FastMathFlags FMF = getDecodedFastMathFlags(Record[OpNum]);
+ if (FMF.any())
+ I->setFastMathFlags(FMF);
+ }
break;
}
Modified: llvm/trunk/lib/Bitcode/Writer/BitcodeWriter.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Bitcode/Writer/BitcodeWriter.cpp?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/lib/Bitcode/Writer/BitcodeWriter.cpp (original)
+++ llvm/trunk/lib/Bitcode/Writer/BitcodeWriter.cpp Wed May 22 08:50:46 2019
@@ -2636,12 +2636,16 @@ void ModuleBitcodeWriter::writeInstructi
Vals.append(IVI->idx_begin(), IVI->idx_end());
break;
}
- case Instruction::Select:
+ case Instruction::Select: {
Code = bitc::FUNC_CODE_INST_VSELECT;
pushValueAndType(I.getOperand(1), InstID, Vals);
pushValue(I.getOperand(2), InstID, Vals);
pushValueAndType(I.getOperand(0), InstID, Vals);
+ uint64_t Flags = getOptimizationFlags(&I);
+ if (Flags != 0)
+ Vals.push_back(Flags);
break;
+ }
case Instruction::ExtractElement:
Code = bitc::FUNC_CODE_INST_EXTRACTELT;
pushValueAndType(I.getOperand(0), InstID, Vals);
Modified: llvm/trunk/test/Bitcode/compatibility.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Bitcode/compatibility.ll?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/test/Bitcode/compatibility.ll (original)
+++ llvm/trunk/test/Bitcode/compatibility.ll Wed May 22 08:50:46 2019
@@ -815,6 +815,34 @@ define void @fastmathflags_binops(float
ret void
}
+define void @fastmathflags_select(i1 %cond, float %op1, float %op2) {
+ %f.nnan = select nnan i1 %cond, float %op1, float %op2
+ ; CHECK: %f.nnan = select nnan i1 %cond, float %op1, float %op2
+ %f.ninf = select ninf i1 %cond, float %op1, float %op2
+ ; CHECK: %f.ninf = select ninf i1 %cond, float %op1, float %op2
+ %f.nsz = select nsz i1 %cond, float %op1, float %op2
+ ; CHECK: %f.nsz = select nsz i1 %cond, float %op1, float %op2
+ %f.arcp = select arcp i1 %cond, float %op1, float %op2
+ ; CHECK: %f.arcp = select arcp i1 %cond, float %op1, float %op2
+ %f.contract = select contract i1 %cond, float %op1, float %op2
+ ; CHECK: %f.contract = select contract i1 %cond, float %op1, float %op2
+ %f.afn = select afn i1 %cond, float %op1, float %op2
+ ; CHECK: %f.afn = select afn i1 %cond, float %op1, float %op2
+ %f.reassoc = select reassoc i1 %cond, float %op1, float %op2
+ ; CHECK: %f.reassoc = select reassoc i1 %cond, float %op1, float %op2
+ %f.fast = select fast i1 %cond, float %op1, float %op2
+ ; CHECK: %f.fast = select fast i1 %cond, float %op1, float %op2
+ ret void
+}
+
+define void @fastmathflags_vector_select(<2 x i1> %cond, <2 x double> %op1, <2 x double> %op2) {
+ %f.nnan.nsz = select nnan nsz <2 x i1> %cond, <2 x double> %op1, <2 x double> %op2
+ ; CHECK: %f.nnan.nsz = select nnan nsz <2 x i1> %cond, <2 x double> %op1, <2 x double> %op2
+ %f.fast = select fast <2 x i1> %cond, <2 x double> %op1, <2 x double> %op2
+ ; CHECK: %f.fast = select fast <2 x i1> %cond, <2 x double> %op1, <2 x double> %op2
+ ret void
+}
+
; Check various fast math flags and floating-point types on calls.
declare float @fmf1()
Modified: llvm/trunk/test/CodeGen/Generic/expand-experimental-reductions.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/Generic/expand-experimental-reductions.ll?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/Generic/expand-experimental-reductions.ll (original)
+++ llvm/trunk/test/CodeGen/Generic/expand-experimental-reductions.ll Wed May 22 08:50:46 2019
@@ -277,7 +277,7 @@ define double @fmax_f64(<2 x double> %ve
; CHECK-NEXT: entry:
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <2 x double> [[VEC:%.*]], <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast ogt <2 x double> [[VEC]], [[RDX_SHUF]]
-; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <2 x i1> [[RDX_MINMAX_CMP]], <2 x double> [[VEC]], <2 x double> [[RDX_SHUF]]
+; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select fast <2 x i1> [[RDX_MINMAX_CMP]], <2 x double> [[VEC]], <2 x double> [[RDX_SHUF]]
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <2 x double> [[RDX_MINMAX_SELECT]], i32 0
; CHECK-NEXT: ret double [[TMP0]]
;
@@ -291,7 +291,7 @@ define double @fmin_f64(<2 x double> %ve
; CHECK-NEXT: entry:
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <2 x double> [[VEC:%.*]], <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast olt <2 x double> [[VEC]], [[RDX_SHUF]]
-; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <2 x i1> [[RDX_MINMAX_CMP]], <2 x double> [[VEC]], <2 x double> [[RDX_SHUF]]
+; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select fast <2 x i1> [[RDX_MINMAX_CMP]], <2 x double> [[VEC]], <2 x double> [[RDX_SHUF]]
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <2 x double> [[RDX_MINMAX_SELECT]], i32 0
; CHECK-NEXT: ret double [[TMP0]]
;
Modified: llvm/trunk/test/Transforms/InstCombine/fast-math.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/fast-math.ll?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/fast-math.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/fast-math.ll Wed May 22 08:50:46 2019
@@ -820,7 +820,7 @@ declare fp128 @fminl(fp128, fp128)
define float @max1(float %a, float %b) {
; CHECK-LABEL: @max1(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp fast ogt float [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], float [[A]], float [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select fast i1 [[TMP1]], float [[A]], float [[B]]
; CHECK-NEXT: ret float [[TMP2]]
;
%c = fpext float %a to double
@@ -833,7 +833,7 @@ define float @max1(float %a, float %b) {
define float @max2(float %a, float %b) {
; CHECK-LABEL: @max2(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp nnan nsz ogt float [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], float [[A]], float [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select nnan nsz i1 [[TMP1]], float [[A]], float [[B]]
; CHECK-NEXT: ret float [[TMP2]]
;
%c = call nnan float @fmaxf(float %a, float %b)
@@ -844,7 +844,7 @@ define float @max2(float %a, float %b) {
define double @max3(double %a, double %b) {
; CHECK-LABEL: @max3(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp fast ogt double [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], double [[A]], double [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select fast i1 [[TMP1]], double [[A]], double [[B]]
; CHECK-NEXT: ret double [[TMP2]]
;
%c = call fast double @fmax(double %a, double %b)
@@ -854,7 +854,7 @@ define double @max3(double %a, double %b
define fp128 @max4(fp128 %a, fp128 %b) {
; CHECK-LABEL: @max4(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp nnan nsz ogt fp128 [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], fp128 [[A]], fp128 [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select nnan nsz i1 [[TMP1]], fp128 [[A]], fp128 [[B]]
; CHECK-NEXT: ret fp128 [[TMP2]]
;
%c = call nnan fp128 @fmaxl(fp128 %a, fp128 %b)
@@ -865,7 +865,7 @@ define fp128 @max4(fp128 %a, fp128 %b) {
define float @min1(float %a, float %b) {
; CHECK-LABEL: @min1(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp nnan nsz olt float [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], float [[A]], float [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select nnan nsz i1 [[TMP1]], float [[A]], float [[B]]
; CHECK-NEXT: ret float [[TMP2]]
;
%c = fpext float %a to double
@@ -878,7 +878,7 @@ define float @min1(float %a, float %b) {
define float @min2(float %a, float %b) {
; CHECK-LABEL: @min2(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp fast olt float [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], float [[A]], float [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select fast i1 [[TMP1]], float [[A]], float [[B]]
; CHECK-NEXT: ret float [[TMP2]]
;
%c = call fast float @fminf(float %a, float %b)
@@ -888,7 +888,7 @@ define float @min2(float %a, float %b) {
define double @min3(double %a, double %b) {
; CHECK-LABEL: @min3(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp nnan nsz olt double [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], double [[A]], double [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select nnan nsz i1 [[TMP1]], double [[A]], double [[B]]
; CHECK-NEXT: ret double [[TMP2]]
;
%c = call nnan double @fmin(double %a, double %b)
@@ -898,7 +898,7 @@ define double @min3(double %a, double %b
define fp128 @min4(fp128 %a, fp128 %b) {
; CHECK-LABEL: @min4(
; CHECK-NEXT: [[TMP1:%.*]] = fcmp fast olt fp128 [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], fp128 [[A]], fp128 [[B]]
+; CHECK-NEXT: [[TMP2:%.*]] = select fast i1 [[TMP1]], fp128 [[A]], fp128 [[B]]
; CHECK-NEXT: ret fp128 [[TMP2]]
;
%c = call fast fp128 @fminl(fp128 %a, fp128 %b)
Modified: llvm/trunk/test/Transforms/InstCombine/pow-sqrt.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/pow-sqrt.ll?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/pow-sqrt.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/pow-sqrt.ll Wed May 22 08:50:46 2019
@@ -36,7 +36,7 @@ define double @pow_libcall_half_approx(d
; CHECK-NEXT: [[SQRT:%.*]] = call afn double @sqrt(double [[X:%.*]])
; CHECK-NEXT: [[ABS:%.*]] = call afn double @llvm.fabs.f64(double [[SQRT]])
; CHECK-NEXT: [[ISINF:%.*]] = fcmp afn oeq double [[X]], 0xFFF0000000000000
-; CHECK-NEXT: [[TMP1:%.*]] = select i1 [[ISINF]], double 0x7FF0000000000000, double [[ABS]]
+; CHECK-NEXT: [[TMP1:%.*]] = select afn i1 [[ISINF]], double 0x7FF0000000000000, double [[ABS]]
; CHECK-NEXT: ret double [[TMP1]]
;
%pow = call afn double @pow(double %x, double 5.0e-01)
@@ -48,7 +48,7 @@ define <2 x double> @pow_intrinsic_half_
; CHECK-NEXT: [[SQRT:%.*]] = call afn <2 x double> @llvm.sqrt.v2f64(<2 x double> [[X:%.*]])
; CHECK-NEXT: [[ABS:%.*]] = call afn <2 x double> @llvm.fabs.v2f64(<2 x double> [[SQRT]])
; CHECK-NEXT: [[ISINF:%.*]] = fcmp afn oeq <2 x double> [[X]], <double 0xFFF0000000000000, double 0xFFF0000000000000>
-; CHECK-NEXT: [[TMP1:%.*]] = select <2 x i1> [[ISINF]], <2 x double> <double 0x7FF0000000000000, double 0x7FF0000000000000>, <2 x double> [[ABS]]
+; CHECK-NEXT: [[TMP1:%.*]] = select afn <2 x i1> [[ISINF]], <2 x double> <double 0x7FF0000000000000, double 0x7FF0000000000000>, <2 x double> [[ABS]]
; CHECK-NEXT: ret <2 x double> [[TMP1]]
;
%pow = call afn <2 x double> @llvm.pow.v2f64(<2 x double> %x, <2 x double> <double 5.0e-01, double 5.0e-01>)
@@ -92,7 +92,7 @@ define double @pow_libcall_half_nsz(doub
; CHECK-LABEL: @pow_libcall_half_nsz(
; CHECK-NEXT: [[SQRT:%.*]] = call nsz double @sqrt(double [[X:%.*]])
; CHECK-NEXT: [[ISINF:%.*]] = fcmp nsz oeq double [[X]], 0xFFF0000000000000
-; CHECK-NEXT: [[TMP1:%.*]] = select i1 [[ISINF]], double 0x7FF0000000000000, double [[SQRT]]
+; CHECK-NEXT: [[TMP1:%.*]] = select nsz i1 [[ISINF]], double 0x7FF0000000000000, double [[SQRT]]
; CHECK-NEXT: ret double [[TMP1]]
;
%pow = call nsz double @pow(double %x, double 5.0e-01)
@@ -103,7 +103,7 @@ define double @pow_intrinsic_half_nsz(do
; CHECK-LABEL: @pow_intrinsic_half_nsz(
; CHECK-NEXT: [[SQRT:%.*]] = call nsz double @llvm.sqrt.f64(double [[X:%.*]])
; CHECK-NEXT: [[ISINF:%.*]] = fcmp nsz oeq double [[X]], 0xFFF0000000000000
-; CHECK-NEXT: [[TMP1:%.*]] = select i1 [[ISINF]], double 0x7FF0000000000000, double [[SQRT]]
+; CHECK-NEXT: [[TMP1:%.*]] = select nsz i1 [[ISINF]], double 0x7FF0000000000000, double [[SQRT]]
; CHECK-NEXT: ret double [[TMP1]]
;
%pow = call nsz double @llvm.pow.f64(double %x, double 5.0e-01)
Modified: llvm/trunk/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll (original)
+++ llvm/trunk/test/Transforms/LoopVectorize/float-minmax-instruction-flag.ll Wed May 22 08:50:46 2019
@@ -74,10 +74,10 @@ define float @minloopattr(float* nocaptu
; CHECK: middle.block:
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x float> [[TMP6]], <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP:%.*]] = fcmp fast olt <4 x float> [[TMP6]], [[RDX_SHUF]]
-; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <4 x i1> [[RDX_MINMAX_CMP]], <4 x float> [[TMP6]], <4 x float> [[RDX_SHUF]]
+; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select fast <4 x i1> [[RDX_MINMAX_CMP]], <4 x float> [[TMP6]], <4 x float> [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <4 x float> [[RDX_MINMAX_SELECT]], <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP2:%.*]] = fcmp fast olt <4 x float> [[RDX_MINMAX_SELECT]], [[RDX_SHUF1]]
-; CHECK-NEXT: [[RDX_MINMAX_SELECT3:%.*]] = select <4 x i1> [[RDX_MINMAX_CMP2]], <4 x float> [[RDX_MINMAX_SELECT]], <4 x float> [[RDX_SHUF1]]
+; CHECK-NEXT: [[RDX_MINMAX_SELECT3:%.*]] = select fast <4 x i1> [[RDX_MINMAX_CMP2]], <4 x float> [[RDX_MINMAX_SELECT]], <4 x float> [[RDX_SHUF1]]
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x float> [[RDX_MINMAX_SELECT3]], i32 0
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 65536, 65536
; CHECK-NEXT: br i1 [[CMP_N]], label [[OUT:%.*]], label [[SCALAR_PH]]
Modified: llvm/trunk/test/Transforms/LoopVectorize/minmax_reduction.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/minmax_reduction.ll?rev=361401&r1=361400&r2=361401&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/minmax_reduction.ll (original)
+++ llvm/trunk/test/Transforms/LoopVectorize/minmax_reduction.ll Wed May 22 08:50:46 2019
@@ -416,7 +416,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @max_red_float(float %max) #0 {
entry:
@@ -442,7 +442,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @max_red_float_ge(float %max) #0 {
entry:
@@ -468,7 +468,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_max_red_float(float %max) #0 {
entry:
@@ -494,7 +494,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_max_red_float_le(float %max) #0 {
entry:
@@ -520,7 +520,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @unordered_max_red_float(float %max) #0 {
entry:
@@ -546,7 +546,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @unordered_max_red_float_ge(float %max) #0 {
entry:
@@ -572,7 +572,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_unordered_max_red_float(float %max) #0 {
entry:
@@ -598,7 +598,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast ogt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_unordered_max_red_float_le(float %max) #0 {
entry:
@@ -627,7 +627,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @min_red_float(float %min) #0 {
entry:
@@ -653,7 +653,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @min_red_float_le(float %min) #0 {
entry:
@@ -679,7 +679,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_min_red_float(float %min) #0 {
entry:
@@ -705,7 +705,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_min_red_float_ge(float %min) #0 {
entry:
@@ -731,7 +731,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @unordered_min_red_float(float %min) #0 {
entry:
@@ -757,7 +757,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @unordered_min_red_float_le(float %min) #0 {
entry:
@@ -783,7 +783,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_unordered_min_red_float(float %min) #0 {
entry:
@@ -809,7 +809,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x float>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define float @inverted_unordered_min_red_float_ge(float %min) #0 {
entry:
@@ -836,7 +836,7 @@ for.end:
; CHECK: select <2 x i1>
; CHECK: middle.block
; CHECK: fcmp fast olt <2 x double>
-; CHECK: select <2 x i1>
+; CHECK: select fast <2 x i1>
define double @min_red_double(double %min) #0 {
entry:
More information about the llvm-commits
mailing list