[llvm] [ValueTracking] Compute KnownFP state from recursive select/phi. (PR #113686)
David Green via llvm-commits
llvm-commits at lists.llvm.org
Sun Oct 27 12:56:35 PDT 2024
https://github.com/davemgreen updated https://github.com/llvm/llvm-project/pull/113686
>From 76239eb7d3b261d17961b741b678e5dfb02df115 Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Sun, 27 Oct 2024 18:13:43 +0000
Subject: [PATCH 1/2] [Attributor] Add nofpclass test for phi+select
recurrences. NFC
---
.../Attributor/nofpclass-phiselect.ll | 176 ++++++++++++++++++
1 file changed, 176 insertions(+)
create mode 100644 llvm/test/Transforms/Attributor/nofpclass-phiselect.ll
diff --git a/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll b/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll
new file mode 100644
index 00000000000000..6635280bc43603
--- /dev/null
+++ b/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll
@@ -0,0 +1,176 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-manifest-internal -S < %s | FileCheck %s
+
+define float @phi_select(i1 %c, float nofpclass(inf) %base, float nofpclass(inf) %arg) {
+; CHECK-LABEL: define float @phi_select
+; CHECK-SAME: (i1 [[C:%.*]], float nofpclass(inf) [[BASE:%.*]], float nofpclass(inf) [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[PHI:%.*]] = phi float [ [[BASE]], [[ENTRY:%.*]] ], [ [[SELECT:%.*]], [[LOOP]] ]
+; CHECK-NEXT: [[SELECT]] = select i1 [[C]], float [[PHI]], float [[ARG]]
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret float [[SELECT]]
+;
+entry:
+ br label %loop
+
+loop:
+ %phi = phi float [ %base, %entry ], [ %select, %loop ]
+ %select = select i1 %c, float %phi, float %arg
+ br i1 %c, label %loop, label %exit
+
+exit:
+ ret float %select
+}
+
+define float @phi_select_onlybase(i1 %c, float nofpclass(inf) %base, float %arg) {
+; CHECK-LABEL: define float @phi_select_onlybase
+; CHECK-SAME: (i1 [[C:%.*]], float nofpclass(inf) [[BASE:%.*]], float [[ARG:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[PHI:%.*]] = phi float [ [[BASE]], [[ENTRY:%.*]] ], [ [[SELECT:%.*]], [[LOOP]] ]
+; CHECK-NEXT: [[SELECT]] = select i1 [[C]], float [[PHI]], float [[ARG]]
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret float [[SELECT]]
+;
+entry:
+ br label %loop
+
+loop:
+ %phi = phi float [ %base, %entry ], [ %select, %loop ]
+ %select = select i1 %c, float %phi, float %arg
+ br i1 %c, label %loop, label %exit
+
+exit:
+ ret float %select
+}
+
+define float @phi_select_onlyarg(i1 %c, float %base, float nofpclass(inf) %arg) {
+; CHECK-LABEL: define float @phi_select_onlyarg
+; CHECK-SAME: (i1 [[C:%.*]], float [[BASE:%.*]], float nofpclass(inf) [[ARG:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[PHI:%.*]] = phi float [ [[BASE]], [[ENTRY:%.*]] ], [ [[SELECT:%.*]], [[LOOP]] ]
+; CHECK-NEXT: [[SELECT]] = select i1 [[C]], float [[PHI]], float [[ARG]]
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret float [[SELECT]]
+;
+entry:
+ br label %loop
+
+loop:
+ %phi = phi float [ %base, %entry ], [ %select, %loop ]
+ %select = select i1 %c, float %phi, float %arg
+ br i1 %c, label %loop, label %exit
+
+exit:
+ ret float %select
+}
+
+define float @phi_phi(i1 %c, float nofpclass(inf) %base, float nofpclass(inf) %arg) {
+; CHECK-LABEL: define float @phi_phi
+; CHECK-SAME: (i1 [[C:%.*]], float nofpclass(inf) [[BASE:%.*]], float nofpclass(inf) [[ARG:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[PHI:%.*]] = phi float [ [[BASE]], [[ENTRY:%.*]] ], [ [[PHI2:%.*]], [[EXIT1:%.*]] ]
+; CHECK-NEXT: br label [[INNER:%.*]]
+; CHECK: inner:
+; CHECK-NEXT: [[PHI2]] = phi float [ [[PHI]], [[LOOP]] ], [ [[ARG]], [[INNER]] ]
+; CHECK-NEXT: br i1 [[C]], label [[INNER]], label [[EXIT1]]
+; CHECK: exit1:
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret float [[PHI2]]
+;
+entry:
+ br label %loop
+
+loop:
+ %phi = phi float [ %base, %entry ], [ %phi2, %exit1 ]
+ br label %inner
+
+inner:
+ %phi2 = phi float [ %phi, %loop ], [ %arg, %inner ]
+ br i1 %c, label %inner, label %exit1
+
+exit1:
+ br i1 %c, label %loop, label %exit
+
+exit:
+ ret float %phi2
+}
+
+define float @phi_phi_onlybase(i1 %c, float nofpclass(inf) %base, float %arg) {
+; CHECK-LABEL: define float @phi_phi_onlybase
+; CHECK-SAME: (i1 [[C:%.*]], float nofpclass(inf) [[BASE:%.*]], float [[ARG:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[PHI:%.*]] = phi float [ [[BASE]], [[ENTRY:%.*]] ], [ [[PHI2:%.*]], [[EXIT1:%.*]] ]
+; CHECK-NEXT: br label [[INNER:%.*]]
+; CHECK: inner:
+; CHECK-NEXT: [[PHI2]] = phi float [ [[PHI]], [[LOOP]] ], [ [[ARG]], [[INNER]] ]
+; CHECK-NEXT: br i1 [[C]], label [[INNER]], label [[EXIT1]]
+; CHECK: exit1:
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret float [[PHI2]]
+;
+entry:
+ br label %loop
+
+loop:
+ %phi = phi float [ %base, %entry ], [ %phi2, %exit1 ]
+ br label %inner
+
+inner:
+ %phi2 = phi float [ %phi, %loop ], [ %arg, %inner ]
+ br i1 %c, label %inner, label %exit1
+
+exit1:
+ br i1 %c, label %loop, label %exit
+
+exit:
+ ret float %phi2
+}
+
+define float @phi_phi_onlyarg(i1 %c, float %base, float nofpclass(inf) %arg) {
+; CHECK-LABEL: define float @phi_phi_onlyarg
+; CHECK-SAME: (i1 [[C:%.*]], float [[BASE:%.*]], float nofpclass(inf) [[ARG:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP:%.*]]
+; CHECK: loop:
+; CHECK-NEXT: [[PHI:%.*]] = phi float [ [[BASE]], [[ENTRY:%.*]] ], [ [[PHI2:%.*]], [[EXIT1:%.*]] ]
+; CHECK-NEXT: br label [[INNER:%.*]]
+; CHECK: inner:
+; CHECK-NEXT: [[PHI2]] = phi float [ [[PHI]], [[LOOP]] ], [ [[ARG]], [[INNER]] ]
+; CHECK-NEXT: br i1 [[C]], label [[INNER]], label [[EXIT1]]
+; CHECK: exit1:
+; CHECK-NEXT: br i1 [[C]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret float [[PHI2]]
+;
+entry:
+ br label %loop
+
+loop:
+ %phi = phi float [ %base, %entry ], [ %phi2, %exit1 ]
+ br label %inner
+
+inner:
+ %phi2 = phi float [ %phi, %loop ], [ %arg, %inner ]
+ br i1 %c, label %inner, label %exit1
+
+exit1:
+ br i1 %c, label %loop, label %exit
+
+exit:
+ ret float %phi2
+}
>From b17b64bde3f1e318b51a04fb9e36c8a1918a0373 Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Sun, 27 Oct 2024 19:55:17 +0000
Subject: [PATCH 2/2] [ValueTracking] Compute KnownFP state from recursive
select/phi.
Given a recursive phi with select:
%p = phi [ 0, entry ], [ %sel, loop]
%sel = select %c, %other, %p
The fp state can be calculated using the knowledge that the select/phi pair can
only be the initial state (0 here) or from %other. This adds a short-cut into
computeKnownFPClass for PHI to detect that the select is recursive back to the
phi, and if so use the state from the other operand.
This helps to address a regression from #83200.
---
llvm/lib/Analysis/ValueTracking.cpp | 7 ++
.../Attributor/nofpclass-phiselect.ll | 2 +-
.../LoopVectorize/ARM/mve-selectandorcost.ll | 4 +-
.../AArch64/predicated-reduction.ll | 81 ++++++++++++++++---
4 files changed, 80 insertions(+), 14 deletions(-)
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index e9ed8b3c862b55..708922e21ee0bb 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -5999,6 +5999,13 @@ void computeKnownFPClass(const Value *V, const APInt &DemandedElts,
if (IncValue == P)
continue;
+ // If the Use is a select of this phi, use the fp class of the other
+ // operand to break the recursion.
+ Value *V;
+ if (match(IncValue, m_Select(m_Value(), m_Specific(P), m_Value(V))) ||
+ match(IncValue, m_Select(m_Value(), m_Value(V), m_Specific(P))))
+ IncValue = V;
+
KnownFPClass KnownSrc;
// Recurse, but cap the recursion to two levels, because we don't want
// to waste time spinning around in loops. We need at least depth 2 to
diff --git a/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll b/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll
index 6635280bc43603..dc40cbf732240f 100644
--- a/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll
+++ b/llvm/test/Transforms/Attributor/nofpclass-phiselect.ll
@@ -2,7 +2,7 @@
; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-manifest-internal -S < %s | FileCheck %s
define float @phi_select(i1 %c, float nofpclass(inf) %base, float nofpclass(inf) %arg) {
-; CHECK-LABEL: define float @phi_select
+; CHECK-LABEL: define nofpclass(inf) float @phi_select
; CHECK-SAME: (i1 [[C:%.*]], float nofpclass(inf) [[BASE:%.*]], float nofpclass(inf) [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-selectandorcost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-selectandorcost.ll
index fc56754166d609..b54d4a97d07be7 100644
--- a/llvm/test/Transforms/LoopVectorize/ARM/mve-selectandorcost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-selectandorcost.ll
@@ -45,8 +45,8 @@ define float @test(ptr nocapture readonly %pA, ptr nocapture readonly %pB, i32 %
; CHECK-NEXT: [[TMP7:%.*]] = fsub fast <4 x float> [[WIDE_LOAD]], [[WIDE_LOAD7]]
; CHECK-NEXT: [[TMP8:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP7]])
; CHECK-NEXT: [[TMP9:%.*]] = fdiv fast <4 x float> [[TMP8]], [[TMP6]]
-; CHECK-NEXT: [[TMP10:%.*]] = fadd fast <4 x float> [[TMP9]], [[VEC_PHI]]
-; CHECK-NEXT: [[PREDPHI]] = select <4 x i1> [[DOTNOT9]], <4 x float> [[VEC_PHI]], <4 x float> [[TMP10]]
+; CHECK-NEXT: [[TMP10:%.*]] = select <4 x i1> [[DOTNOT9]], <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, <4 x float> [[TMP9]]
+; CHECK-NEXT: [[PREDPHI]] = fadd fast <4 x float> [[VEC_PHI]], [[TMP10]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
diff --git a/llvm/test/Transforms/PhaseOrdering/AArch64/predicated-reduction.ll b/llvm/test/Transforms/PhaseOrdering/AArch64/predicated-reduction.ll
index 7274e952567693..9e9d1e3bab2ce4 100644
--- a/llvm/test/Transforms/PhaseOrdering/AArch64/predicated-reduction.ll
+++ b/llvm/test/Transforms/PhaseOrdering/AArch64/predicated-reduction.ll
@@ -12,26 +12,79 @@ define nofpclass(nan inf) double @monte_simple(i32 noundef %nblocks, i32 noundef
; CHECK-NEXT: br i1 [[CMP8]], label %[[FOR_BODY_PREHEADER:.*]], label %[[FOR_END:.*]]
; CHECK: [[FOR_BODY_PREHEADER]]:
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[RAND_BLOCK_LENGTH]] to i64
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[RAND_BLOCK_LENGTH]], 4
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[FOR_BODY_PREHEADER23:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[WIDE_TRIP_COUNT]], 2147483644
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x double> poison, double [[Y]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x double> [[BROADCAST_SPLATINSERT]], <2 x double> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT19:%.*]] = insertelement <2 x double> poison, double [[Z]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT20:%.*]] = shufflevector <2 x double> [[BROADCAST_SPLATINSERT19]], <2 x double> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x double> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP18:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI15:%.*]] = phi <2 x double> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP19:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI16:%.*]] = phi <2 x double> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP14:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_PHI17:%.*]] = phi <2 x double> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP15:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[SAMPLES]], i64 [[INDVARS_IV]]
+; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds i8, ptr [[ARRAYIDX]], i64 8
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[ARRAYIDX]], align 4
+; CHECK-NEXT: [[WIDE_LOAD18:%.*]] = load <2 x float>, ptr [[TMP23]], align 4
+; CHECK-NEXT: [[TMP2:%.*]] = fpext <2 x float> [[WIDE_LOAD]] to <2 x double>
+; CHECK-NEXT: [[TMP3:%.*]] = fpext <2 x float> [[WIDE_LOAD18]] to <2 x double>
+; CHECK-NEXT: [[TMP4:%.*]] = fmul fast <2 x double> [[BROADCAST_SPLAT]], [[TMP2]]
+; CHECK-NEXT: [[TMP5:%.*]] = fmul fast <2 x double> [[BROADCAST_SPLAT]], [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = fsub fast <2 x double> [[TMP4]], [[BROADCAST_SPLAT20]]
+; CHECK-NEXT: [[TMP7:%.*]] = fsub fast <2 x double> [[TMP5]], [[BROADCAST_SPLAT20]]
+; CHECK-NEXT: [[TMP8:%.*]] = fcmp fast ogt <2 x double> [[TMP6]], zeroinitializer
+; CHECK-NEXT: [[TMP9:%.*]] = fcmp fast ogt <2 x double> [[TMP7]], zeroinitializer
+; CHECK-NEXT: [[TMP10:%.*]] = fmul fast <2 x double> [[TMP6]], [[TMP6]]
+; CHECK-NEXT: [[TMP11:%.*]] = fmul fast <2 x double> [[TMP7]], [[TMP7]]
+; CHECK-NEXT: [[TMP12:%.*]] = tail call fast <2 x double> @llvm.maxnum.v2f64(<2 x double> [[TMP6]], <2 x double> <double -0.000000e+00, double -0.000000e+00>)
+; CHECK-NEXT: [[TMP13:%.*]] = tail call fast <2 x double> @llvm.maxnum.v2f64(<2 x double> [[TMP7]], <2 x double> <double -0.000000e+00, double -0.000000e+00>)
+; CHECK-NEXT: [[TMP14]] = fadd fast <2 x double> [[TMP12]], [[VEC_PHI16]]
+; CHECK-NEXT: [[TMP15]] = fadd fast <2 x double> [[TMP13]], [[VEC_PHI17]]
+; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP8]], <2 x double> [[TMP10]], <2 x double> <double -0.000000e+00, double -0.000000e+00>
+; CHECK-NEXT: [[TMP17:%.*]] = select <2 x i1> [[TMP9]], <2 x double> [[TMP11]], <2 x double> <double -0.000000e+00, double -0.000000e+00>
+; CHECK-NEXT: [[TMP18]] = fadd fast <2 x double> [[TMP16]], [[VEC_PHI]]
+; CHECK-NEXT: [[TMP19]] = fadd fast <2 x double> [[TMP17]], [[VEC_PHI15]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDVARS_IV]], 4
+; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP20]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd fast <2 x double> [[TMP19]], [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = tail call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> [[BIN_RDX]])
+; CHECK-NEXT: [[BIN_RDX21:%.*]] = fadd fast <2 x double> [[TMP15]], [[TMP14]]
+; CHECK-NEXT: [[TMP22:%.*]] = tail call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> [[BIN_RDX21]])
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[WIDE_TRIP_COUNT]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[FOR_END_LOOPEXIT:.*]], label %[[FOR_BODY_PREHEADER23]]
+; CHECK: [[FOR_BODY_PREHEADER23]]:
+; CHECK-NEXT: [[INDVARS_IV_PH:%.*]] = phi i64 [ 0, %[[FOR_BODY_PREHEADER]] ], [ [[N_VEC]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: [[V1_012_PH:%.*]] = phi double [ 0.000000e+00, %[[FOR_BODY_PREHEADER]] ], [ [[TMP21]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: [[V0_011_PH:%.*]] = phi double [ 0.000000e+00, %[[FOR_BODY_PREHEADER]] ], [ [[TMP22]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: br label %[[FOR_BODY:.*]]
; CHECK: [[FOR_BODY]]:
-; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[FOR_BODY_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; CHECK-NEXT: [[V1_011:%.*]] = phi double [ 0.000000e+00, %[[FOR_BODY_PREHEADER]] ], [ [[V1_1:%.*]], %[[FOR_BODY]] ]
-; CHECK-NEXT: [[V0_010:%.*]] = phi double [ 0.000000e+00, %[[FOR_BODY_PREHEADER]] ], [ [[V0_1:%.*]], %[[FOR_BODY]] ]
-; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[SAMPLES]], i64 [[INDVARS_IV]]
-; CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[ARRAYIDX]], align 4
+; CHECK-NEXT: [[INDVARS_IV1:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY]] ], [ [[INDVARS_IV_PH]], %[[FOR_BODY_PREHEADER23]] ]
+; CHECK-NEXT: [[V1_012:%.*]] = phi double [ [[V1_2:%.*]], %[[FOR_BODY]] ], [ [[V1_012_PH]], %[[FOR_BODY_PREHEADER23]] ]
+; CHECK-NEXT: [[V0_011:%.*]] = phi double [ [[V0_2:%.*]], %[[FOR_BODY]] ], [ [[V0_011_PH]], %[[FOR_BODY_PREHEADER23]] ]
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds float, ptr [[SAMPLES]], i64 [[INDVARS_IV1]]
+; CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[ARRAYIDX1]], align 4
; CHECK-NEXT: [[CONV:%.*]] = fpext float [[TMP0]] to double
; CHECK-NEXT: [[MUL:%.*]] = fmul fast double [[Y]], [[CONV]]
; CHECK-NEXT: [[SUB:%.*]] = fsub fast double [[MUL]], [[Z]]
; CHECK-NEXT: [[CMP1:%.*]] = fcmp fast ogt double [[SUB]], 0.000000e+00
-; CHECK-NEXT: [[ADD:%.*]] = fadd fast double [[SUB]], [[V0_010]]
; CHECK-NEXT: [[MUL3:%.*]] = fmul fast double [[SUB]], [[SUB]]
-; CHECK-NEXT: [[ADD4:%.*]] = fadd fast double [[MUL3]], [[V1_011]]
-; CHECK-NEXT: [[V0_1]] = select i1 [[CMP1]], double [[ADD]], double [[V0_010]]
-; CHECK-NEXT: [[V1_1]] = select i1 [[CMP1]], double [[ADD4]], double [[V1_011]]
-; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT: [[ADD8:%.*]] = tail call fast double @llvm.maxnum.f64(double [[SUB]], double -0.000000e+00)
+; CHECK-NEXT: [[V0_2]] = fadd fast double [[ADD8]], [[V0_011]]
+; CHECK-NEXT: [[ADD4:%.*]] = select i1 [[CMP1]], double [[MUL3]], double -0.000000e+00
+; CHECK-NEXT: [[V1_2]] = fadd fast double [[ADD4]], [[V1_012]]
+; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV1]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END_LOOPEXIT:.*]], label %[[FOR_BODY]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END_LOOPEXIT]], label %[[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[FOR_END_LOOPEXIT]]:
+; CHECK-NEXT: [[V0_1:%.*]] = phi double [ [[TMP22]], %[[MIDDLE_BLOCK]] ], [ [[V0_2]], %[[FOR_BODY]] ]
+; CHECK-NEXT: [[V1_1:%.*]] = phi double [ [[TMP21]], %[[MIDDLE_BLOCK]] ], [ [[V1_2]], %[[FOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = fadd fast double [[V1_1]], [[V0_1]]
; CHECK-NEXT: br label %[[FOR_END]]
; CHECK: [[FOR_END]]:
@@ -292,3 +345,9 @@ declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture)
declare void @resample(i32 noundef, ptr noundef)
declare double @llvm.exp2.f64(double)
declare void @llvm.lifetime.end.p0(i64 immarg, ptr nocapture)
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
+;.
More information about the llvm-commits
mailing list