[ValueTracking] Do not use FMF from fcmp (#142266)

This patch introduces an FMF parameter for
`matchDecomposedSelectPattern` to pass FMF flags from select, instead of
fcmp.

Closes #137998.
Closes #141017.

Author: dtcxzyw

llvm/include/llvm/Analysis/ValueTracking.h

@@ -889,7 +889,8 @@ inline SelectPatternResult matchSelectPattern(const Value *V, const Value *&LHS,
 /// predicate and given values as its true/false operands would match.
 LLVM_ABI SelectPatternResult matchDecomposedSelectPattern(
     CmpInst *CmpI, Value *TrueVal, Value *FalseVal, Value *&LHS, Value *&RHS,
-    Instruction::CastOps *CastOp = nullptr, unsigned Depth = 0);
+    FastMathFlags FMF = FastMathFlags(), Instruction::CastOps *CastOp = nullptr,
+    unsigned Depth = 0);
 
 /// Determine the pattern for predicate `X Pred Y ? X : Y`.
 LLVM_ABI SelectPatternResult getSelectPattern(

llvm/lib/Analysis/ValueTracking.cpp

@@ -8898,19 +8898,20 @@ SelectPatternResult llvm::matchSelectPattern(Value *V, Value *&LHS, Value *&RHS,
   Value *TrueVal = SI->getTrueValue();
   Value *FalseVal = SI->getFalseValue();
 
-  return llvm::matchDecomposedSelectPattern(CmpI, TrueVal, FalseVal, LHS, RHS,
-                                            CastOp, Depth);
+  return llvm::matchDecomposedSelectPattern(
+      CmpI, TrueVal, FalseVal, LHS, RHS,
+      isa<FPMathOperator>(SI) ? SI->getFastMathFlags() : FastMathFlags(),
+      CastOp, Depth);
 }
 
 SelectPatternResult llvm::matchDecomposedSelectPattern(
     CmpInst *CmpI, Value *TrueVal, Value *FalseVal, Value *&LHS, Value *&RHS,
-    Instruction::CastOps *CastOp, unsigned Depth) {
+    FastMathFlags FMF, Instruction::CastOps *CastOp, unsigned Depth) {
   CmpInst::Predicate Pred = CmpI->getPredicate();
   Value *CmpLHS = CmpI->getOperand(0);
   Value *CmpRHS = CmpI->getOperand(1);
-  FastMathFlags FMF;
-  if (isa<FPMathOperator>(CmpI))
-    FMF = CmpI->getFastMathFlags();
+  if (isa<FPMathOperator>(CmpI) && CmpI->hasNoNaNs())
+    FMF.setNoNaNs();
 
   // Bail out early.
   if (CmpI->isEquality())

llvm/test/CodeGen/AArch64/arm64-fmax-safe.ll

@@ -53,3 +53,22 @@ define i64 @test_integer(i64  %in) {
   %val = select i1 %cmp, i64 0, i64 %in
   ret i64 %val
 }
+
+; Make sure we don't translate it into fminnm when the nsz flag is set on the fcmp.
+define float @minnum_fcmp_nsz(float %x, float %y) {
+; CHECK-LABEL: minnum_fcmp_nsz:
+  %cmp = fcmp nnan nsz ole float %x, %y
+  %sel = select i1 %cmp, float %x, float %y
+  ret float %sel
+; CHECK-NOT: fminnm
+; CHECK: fcsel s0, s0, s1, le
+}
+
+; Make sure we translate it into fminnm when the nsz flag is set on the select.
+define float @minnum_select_nsz(float %x, float %y) {
+; CHECK-LABEL: minnum_select_nsz:
+  %cmp = fcmp nnan ole float %x, %y
+  %sel = select nsz i1 %cmp, float %x, float %y
+  ret float %sel
+; CHECK: fminnm s0, s0, s1
+}

llvm/test/CodeGen/AMDGPU/select-flags-to-fmin-fmax.ll

@@ -355,17 +355,15 @@ define <2 x float> @v_test_fmin_legacy_ule_v2f32_nnan_nsz_flag(<2 x float> %a, <
 ; GFX7-LABEL: v_test_fmin_legacy_ule_v2f32_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_min_legacy_f32_e32 v0, v2, v0
-; GFX7-NEXT:    v_min_legacy_f32_e32 v1, v3, v1
+; GFX7-NEXT:    v_min_f32_e32 v0, v0, v2
+; GFX7-NEXT:    v_min_f32_e32 v1, v1, v3
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX9-LABEL: v_test_fmin_legacy_ule_v2f32_nnan_nsz_flag:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX9-NEXT:    v_cmp_ngt_f32_e32 vcc, v0, v2
-; GFX9-NEXT:    v_cndmask_b32_e32 v0, v2, v0, vcc
-; GFX9-NEXT:    v_cmp_ngt_f32_e32 vcc, v1, v3
-; GFX9-NEXT:    v_cndmask_b32_e32 v1, v3, v1, vcc
+; GFX9-NEXT:    v_min_f32_e32 v0, v0, v2
+; GFX9-NEXT:    v_min_f32_e32 v1, v1, v3
 ; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX12-LABEL: v_test_fmin_legacy_ule_v2f32_nnan_nsz_flag:
@@ -375,12 +373,7 @@ define <2 x float> @v_test_fmin_legacy_ule_v2f32_nnan_nsz_flag(<2 x float> %a, <
 ; GFX12-NEXT:    s_wait_samplecnt 0x0
 ; GFX12-NEXT:    s_wait_bvhcnt 0x0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    v_cmp_ngt_f32_e32 vcc_lo, v0, v2
-; GFX12-NEXT:    s_wait_alu 0xfffd
-; GFX12-NEXT:    v_cndmask_b32_e32 v0, v2, v0, vcc_lo
-; GFX12-NEXT:    v_cmp_ngt_f32_e32 vcc_lo, v1, v3
-; GFX12-NEXT:    s_wait_alu 0xfffd
-; GFX12-NEXT:    v_cndmask_b32_e32 v1, v3, v1, vcc_lo
+; GFX12-NEXT:    v_dual_min_num_f32 v0, v0, v2 :: v_dual_min_num_f32 v1, v1, v3
 ; GFX12-NEXT:    s_setpc_b64 s[30:31]
   %cmp = fcmp ule <2 x float> %a, %b
   %val = select nnan nsz <2 x i1> %cmp, <2 x float> %a, <2 x float> %b
@@ -499,17 +492,15 @@ define <2 x float> @v_test_fmax_legacy_uge_v2f32_nnan_nsz_flag(<2 x float> %a, <
 ; GFX7-LABEL: v_test_fmax_legacy_uge_v2f32_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_max_legacy_f32_e32 v0, v2, v0
-; GFX7-NEXT:    v_max_legacy_f32_e32 v1, v3, v1
+; GFX7-NEXT:    v_max_f32_e32 v0, v0, v2
+; GFX7-NEXT:    v_max_f32_e32 v1, v1, v3
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX9-LABEL: v_test_fmax_legacy_uge_v2f32_nnan_nsz_flag:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX9-NEXT:    v_cmp_nlt_f32_e32 vcc, v0, v2
-; GFX9-NEXT:    v_cndmask_b32_e32 v0, v2, v0, vcc
-; GFX9-NEXT:    v_cmp_nlt_f32_e32 vcc, v1, v3
-; GFX9-NEXT:    v_cndmask_b32_e32 v1, v3, v1, vcc
+; GFX9-NEXT:    v_max_f32_e32 v0, v0, v2
+; GFX9-NEXT:    v_max_f32_e32 v1, v1, v3
 ; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX12-LABEL: v_test_fmax_legacy_uge_v2f32_nnan_nsz_flag:
@@ -519,12 +510,7 @@ define <2 x float> @v_test_fmax_legacy_uge_v2f32_nnan_nsz_flag(<2 x float> %a, <
 ; GFX12-NEXT:    s_wait_samplecnt 0x0
 ; GFX12-NEXT:    s_wait_bvhcnt 0x0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    v_cmp_nlt_f32_e32 vcc_lo, v0, v2
-; GFX12-NEXT:    s_wait_alu 0xfffd
-; GFX12-NEXT:    v_cndmask_b32_e32 v0, v2, v0, vcc_lo
-; GFX12-NEXT:    v_cmp_nlt_f32_e32 vcc_lo, v1, v3
-; GFX12-NEXT:    s_wait_alu 0xfffd
-; GFX12-NEXT:    v_cndmask_b32_e32 v1, v3, v1, vcc_lo
+; GFX12-NEXT:    v_dual_max_num_f32 v0, v0, v2 :: v_dual_max_num_f32 v1, v1, v3
 ; GFX12-NEXT:    s_setpc_b64 s[30:31]
   %cmp = fcmp uge <2 x float> %a, %b
   %val = select nnan nsz <2 x i1> %cmp, <2 x float> %a, <2 x float> %b
@@ -673,10 +659,10 @@ define half @v_test_fmin_legacy_ule_f16_nnan_nsz_flag(half %a, half %b) {
 ; GFX7-LABEL: v_test_fmin_legacy_ule_f16_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
 ; GFX7-NEXT:    v_min_f32_e32 v0, v0, v1
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
@@ -852,10 +838,10 @@ define half @v_test_fmax_legacy_uge_f16_nnan_nsz_flag(half %a, half %b) {
 ; GFX7-LABEL: v_test_fmax_legacy_uge_f16_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
 ; GFX7-NEXT:    v_max_f32_e32 v0, v0, v1
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
@@ -1097,16 +1083,16 @@ define <2 x half> @v_test_fmin_legacy_ule_v2f16_nnan_nsz_flag(<2 x half> %a, <2
 ; GFX7-LABEL: v_test_fmin_legacy_ule_v2f16_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v3, v3
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
 ; GFX7-NEXT:    v_cvt_f32_f16_e32 v3, v3
-; GFX7-NEXT:    v_min_legacy_f32_e32 v0, v2, v0
-; GFX7-NEXT:    v_min_legacy_f32_e32 v1, v3, v1
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; GFX7-NEXT:    v_min_f32_e32 v0, v0, v2
+; GFX7-NEXT:    v_min_f32_e32 v1, v1, v3
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX9-LABEL: v_test_fmin_legacy_ule_v2f16_nnan_nsz_flag:
@@ -1337,16 +1323,16 @@ define <2 x half> @v_test_fmax_legacy_uge_v2f16_nnan_nsz_flag(<2 x half> %a, <2
 ; GFX7-LABEL: v_test_fmax_legacy_uge_v2f16_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v3, v3
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
 ; GFX7-NEXT:    v_cvt_f32_f16_e32 v3, v3
-; GFX7-NEXT:    v_max_legacy_f32_e32 v0, v2, v0
-; GFX7-NEXT:    v_max_legacy_f32_e32 v1, v3, v1
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; GFX7-NEXT:    v_max_f32_e32 v0, v0, v2
+; GFX7-NEXT:    v_max_f32_e32 v1, v1, v3
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX9-LABEL: v_test_fmax_legacy_uge_v2f16_nnan_nsz_flag:
@@ -1667,26 +1653,26 @@ define <4 x half> @v_test_fmin_legacy_ule_v4f16_nnan_nsz_flag(<4 x half> %a, <4
 ; GFX7-LABEL: v_test_fmin_legacy_ule_v4f16_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v3, v3
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v7, v7
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v6, v6
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v4, v4
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v3, v3
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v5, v5
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v3, v3
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v4, v4
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v5, v5
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v6, v6
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v4, v4
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
 ; GFX7-NEXT:    v_cvt_f32_f16_e32 v7, v7
-; GFX7-NEXT:    v_min_legacy_f32_e32 v0, v4, v0
-; GFX7-NEXT:    v_min_legacy_f32_e32 v1, v5, v1
-; GFX7-NEXT:    v_min_legacy_f32_e32 v2, v6, v2
-; GFX7-NEXT:    v_min_legacy_f32_e32 v3, v7, v3
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v6, v6
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v5, v5
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v4, v4
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v3, v3
+; GFX7-NEXT:    v_min_f32_e32 v0, v0, v4
+; GFX7-NEXT:    v_min_f32_e32 v1, v1, v5
+; GFX7-NEXT:    v_min_f32_e32 v2, v2, v6
+; GFX7-NEXT:    v_min_f32_e32 v3, v3, v7
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX9-LABEL: v_test_fmin_legacy_ule_v4f16_nnan_nsz_flag:
@@ -2009,26 +1995,26 @@ define <4 x half> @v_test_fmax_legacy_uge_v4f16_nnan_nsz_flag(<4 x half> %a, <4
 ; GFX7-LABEL: v_test_fmax_legacy_uge_v4f16_nnan_nsz_flag:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v3, v3
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v7, v7
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v6, v6
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f16_f32_e32 v4, v4
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v3, v3
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v2, v2
 ; GFX7-NEXT:    v_cvt_f16_f32_e32 v5, v5
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v3, v3
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v4, v4
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v5, v5
-; GFX7-NEXT:    v_cvt_f32_f16_e32 v6, v6
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v4, v4
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f16_f32_e32 v1, v1
 ; GFX7-NEXT:    v_cvt_f32_f16_e32 v7, v7
-; GFX7-NEXT:    v_max_legacy_f32_e32 v0, v4, v0
-; GFX7-NEXT:    v_max_legacy_f32_e32 v1, v5, v1
-; GFX7-NEXT:    v_max_legacy_f32_e32 v2, v6, v2
-; GFX7-NEXT:    v_max_legacy_f32_e32 v3, v7, v3
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v6, v6
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v5, v5
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v4, v4
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v0, v0
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v2, v2
+; GFX7-NEXT:    v_cvt_f32_f16_e32 v3, v3
+; GFX7-NEXT:    v_max_f32_e32 v0, v0, v4
+; GFX7-NEXT:    v_max_f32_e32 v1, v1, v5
+; GFX7-NEXT:    v_max_f32_e32 v2, v2, v6
+; GFX7-NEXT:    v_max_f32_e32 v3, v3, v7
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX9-LABEL: v_test_fmax_legacy_uge_v4f16_nnan_nsz_flag:

llvm/test/CodeGen/ARM/fp16-vminmaxnm-safe.ll

@@ -517,9 +517,9 @@ define half @fp16_vminmaxnm_e_0(half %a) {
 ; CHECK-NEXT:    .short 0x0000 @ half 0
 entry:
   %cmp1 = fcmp nsz ole half 0., %a
-  %cond1 = select i1 %cmp1, half 0., half %a
+  %cond1 = select nsz i1 %cmp1, half 0., half %a
   %cmp2 = fcmp nsz uge half 0., %cond1
-  %cond2 = select i1 %cmp2, half 0., half %cond1
+  %cond2 = select nsz i1 %cmp2, half 0., half %cond1
   ret half %cond2
 }
 
@@ -540,7 +540,7 @@ define half @fp16_vminmaxnm_e_neg0(half %a) {
 ; CHECK-NEXT:    .short 0x8000 @ half -0
 entry:
   %cmp1 = fcmp nsz ule half -0., %a
-  %cond1 = select i1 %cmp1, half -0., half %a
+  %cond1 = select nsz i1 %cmp1, half -0., half %a
   %cmp2 = fcmp nsz oge half -0., %cond1
   %cond2 = select i1 %cmp2, half -0., half %cond1
   ret half %cond2