[instcombine] Optimise for zero initialisation of product given fast flags are enabled

Currently, clang ignores the 0 initialisation in finite math
For example:

```
double f_prod = 0;
double arr[1000];
for (size_t i = 0; i < 1000; i++) {
  f_prod *= arr[i];
 }
```
Clang will ignore that `f_prod` is set to zero and it will generate assembly to iterate over the loop.

Reviewed By: fhahn, spatel

Differential Revision: https://reviews.llvm.org/D131672

Author: Zain Jaffal

llvm/lib/Analysis/ValueTracking.cpp

@@ -6538,7 +6538,8 @@ bool llvm::matchSimpleRecurrence(const PHINode *P, BinaryOperator *&BO,
     case Instruction::Sub:
     case Instruction::And:
     case Instruction::Or:
-    case Instruction::Mul: {
+    case Instruction::Mul:
+    case Instruction::FMul: {
       Value *LL = LU->getOperand(0);
       Value *LR = LU->getOperand(1);
       // Find a recurrence.

llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp

@@ -15,6 +15,7 @@
 #include "llvm/ADT/APInt.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/Constants.h"
@@ -672,6 +673,15 @@ Instruction *InstCombinerImpl::visitFMul(BinaryOperator &I) {
     }
   }
 
+  // Simplify FMUL recurrences starting with 0.0 to 0.0 if nnan and nsz are set.
+  // Given a phi node with entry value as 0 and it used in fmul operation,
+  // we can replace fmul with 0 safely and eleminate loop operation.
+  PHINode *PN = nullptr;
+  Value *Start = nullptr, *Step = nullptr;
+  if (matchSimpleRecurrence(&I, PN, Start, Step) && I.hasNoNaNs() &&
+      I.hasNoSignedZeros() && match(Start, m_Zero()))
+    return replaceInstUsesWith(I, Start);
+
   return nullptr;
 }
 

llvm/test/Transforms/InstCombine/remove-loop-phi-fastmul.ll

@@ -6,15 +6,11 @@ define double @test_mul_fast_flags(ptr %arr_d) {
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I_02:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[F_PROD_01:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[MUL:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [1000 x double], ptr [[ARR_D:%.*]], i64 0, i64 [[I_02]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load double, ptr [[ARRAYIDX]], align 8
-; CHECK-NEXT:    [[MUL]] = fmul fast double [[F_PROD_01]], [[TMP0]]
 ; CHECK-NEXT:    [[INC]] = add i64 [[I_02]], 1
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[INC]], 1000
 ; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[END:%.*]]
 ; CHECK:       end:
-; CHECK-NEXT:    ret double [[MUL]]
+; CHECK-NEXT:    ret double 0.000000e+00
 ;
 entry:
   br label %for.body
@@ -40,15 +36,11 @@ define double @test_nsz_nnan_flags_enabled(ptr %arr_d) {
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I_02:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[F_PROD_01:%.*]] = phi double [ 0.000000e+00, [[ENTRY]] ], [ [[MUL:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [1000 x double], ptr [[ARR_D:%.*]], i64 0, i64 [[I_02]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load double, ptr [[ARRAYIDX]], align 8
-; CHECK-NEXT:    [[MUL]] = fmul nnan nsz double [[F_PROD_01]], [[TMP0]]
 ; CHECK-NEXT:    [[INC]] = add i64 [[I_02]], 1
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[INC]], 1000
 ; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[END:%.*]]
 ; CHECK:       end:
-; CHECK-NEXT:    ret double [[MUL]]
+; CHECK-NEXT:    ret double 0.000000e+00
 ;
 entry:
   br label %for.body