[llvm] InstCombine: extend select-equiv to support vectors (PR #111966)

Ramkumar Ramachandra via llvm-commits llvm-commits at lists.llvm.org
Mon Oct 14 07:36:33 PDT 2024


https://github.com/artagnon updated https://github.com/llvm/llvm-project/pull/111966

>From b52b98d6e30ce6c288e32bbb814d54f2256a1314 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Wed, 9 Oct 2024 16:05:16 +0100
Subject: [PATCH 1/2] InstCombine/test: cover foldSelectValueEquivalence

Write dedicated tests for foldSelectValueEquivalence, demonstrating that
it does not perform many GVN-like replacements when:

- the comparison is a vector-type
- the comparison is a floating-point type

as a prelude to fixing these deficiencies.
---
 .../InstCombine/select-value-equivalence.ll   | 311 ++++++++++++++++++
 1 file changed, 311 insertions(+)
 create mode 100644 llvm/test/Transforms/InstCombine/select-value-equivalence.ll

diff --git a/llvm/test/Transforms/InstCombine/select-value-equivalence.ll b/llvm/test/Transforms/InstCombine/select-value-equivalence.ll
new file mode 100644
index 00000000000000..62c8a2c981c5b0
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/select-value-equivalence.ll
@@ -0,0 +1,311 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes=instcombine -S %s | FileCheck %s
+
+define <2 x i8> @select_icmp_insertelement_eq(<2 x i8> %x, <2 x i8> %y, i8 %i) {
+; CHECK-LABEL: define <2 x i8> @select_icmp_insertelement_eq(
+; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], i8 [[I:%.*]]) {
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
+; CHECK-NEXT:    [[INSERT:%.*]] = insertelement <2 x i8> [[Y]], i8 0, i8 [[I]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP]], <2 x i8> [[INSERT]], <2 x i8> [[X]]
+; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
+;
+  %cmp = icmp eq <2 x i8> %y, <i8 2, i8 2>
+  %insert = insertelement <2 x i8> %y, i8 0, i8 %i
+  %retval = select <2 x i1> %cmp, <2 x i8> %insert, <2 x i8> %x
+  ret <2 x i8> %retval
+}
+
+define <2 x i8> @select_icmp_insertelement_ne(<2 x i8> %x, <2 x i8> %y, i8 %i) {
+; CHECK-LABEL: define <2 x i8> @select_icmp_insertelement_ne(
+; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], i8 [[I:%.*]]) {
+; CHECK-NEXT:    [[CMP_NOT:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
+; CHECK-NEXT:    [[INSERT:%.*]] = insertelement <2 x i8> [[Y]], i8 0, i8 [[I]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP_NOT]], <2 x i8> [[INSERT]], <2 x i8> [[X]]
+; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
+;
+  %cmp = icmp ne <2 x i8> %y, <i8 2, i8 2>
+  %insert = insertelement <2 x i8> %y, i8 0, i8 %i
+  %retval = select <2 x i1> %cmp, <2 x i8> %x, <2 x i8> %insert
+  ret <2 x i8> %retval
+}
+
+define <2 x i8> @select_icmp_shufflevector_identity(<2 x i8> %x, <2 x i8> %y) {
+; CHECK-LABEL: define <2 x i8> @select_icmp_shufflevector_identity(
+; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]]) {
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP]], <2 x i8> <i8 2, i8 2>, <2 x i8> [[X]]
+; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
+;
+  %cmp = icmp eq <2 x i8> %y, <i8 2, i8 2>
+  %shuffle = shufflevector <2 x i8> %y, <2 x i8> poison, <2 x i32> <i32 0, i32 1>
+  %retval = select <2 x i1> %cmp, <2 x i8> %shuffle, <2 x i8> %x
+  ret <2 x i8> %retval
+}
+
+define <4 x i8> @select_icmp_shufflevector_select(<4 x i8> %x, <4 x i8> %y, <4 x i8> %z) {
+; CHECK-LABEL: define <4 x i8> @select_icmp_shufflevector_select(
+; CHECK-SAME: <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i8> [[Z:%.*]]) {
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <4 x i8> [[Y]], <i8 2, i8 2, i8 2, i8 2>
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <4 x i8> [[Z]], <4 x i8> [[Y]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <4 x i1> [[CMP]], <4 x i8> [[SHUFFLE]], <4 x i8> [[X]]
+; CHECK-NEXT:    ret <4 x i8> [[RETVAL]]
+;
+  %cmp = icmp eq <4 x i8> %y, <i8 2, i8 2, i8 2, i8 2>
+  %shuffle = shufflevector <4 x i8> %y, <4 x i8> %z, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
+  %retval = select <4 x i1> %cmp, <4 x i8> %shuffle, <4 x i8> %x
+  ret <4 x i8> %retval
+}
+
+define <2 x i8> @select_icmp_shufflevector_lanecrossing(<2 x i8> %x, <2 x i8> %y) {
+; CHECK-LABEL: define <2 x i8> @select_icmp_shufflevector_lanecrossing(
+; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]]) {
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i8> [[Y]], <2 x i8> poison, <2 x i32> <i32 1, i32 0>
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP]], <2 x i8> [[SHUFFLE]], <2 x i8> [[X]]
+; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
+;
+  %cmp = icmp eq <2 x i8> %y, <i8 2, i8 2>
+  %shuffle = shufflevector <2 x i8> %y, <2 x i8> poison, <2 x i32> <i32 1, i32 0>
+  %retval = select <2 x i1> %cmp, <2 x i8> %shuffle, <2 x i8> %x
+  ret <2 x i8> %retval
+}
+
+declare <2 x i8> @fn(<2 x i8>)
+
+define <2 x i8> @select_icmp_call_possibly_lanecrossing(<2 x i8> %x, <2 x i8> %y) {
+; CHECK-LABEL: define <2 x i8> @select_icmp_call_possibly_lanecrossing(
+; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]]) {
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
+; CHECK-NEXT:    [[CALL:%.*]] = call <2 x i8> @fn(<2 x i8> [[Y]])
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP]], <2 x i8> [[CALL]], <2 x i8> [[X]]
+; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
+;
+  %cmp = icmp eq <2 x i8> %y, <i8 2, i8 2>
+  %call = call <2 x i8> @fn(<2 x i8> %y)
+  %retval = select <2 x i1> %cmp, <2 x i8> %call, <2 x i8> %x
+  ret <2 x i8> %retval
+}
+
+define float @select_fcmp_fadd_oeq_not_zero(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_oeq_not_zero(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp oeq float [[Y]], 2.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[FADD]], float [[X]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp oeq float %y, 2.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %fadd, float %x
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_une_not_zero(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_une_not_zero(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp une float [[Y]], 2.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[X]], float [[FADD]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp une float %y, 2.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %x, float %fadd
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_ueq_nnan_not_zero(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_ueq_nnan_not_zero(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp nnan ueq float [[Y]], 2.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[FADD]], float [[X]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp nnan ueq float %y, 2.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %fadd, float %x
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_one_nnan_not_zero(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_one_nnan_not_zero(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp nnan one float [[Y]], 2.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[X]], float [[FADD]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp nnan one float %y, 2.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %x, float %fadd
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_ueq(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_ueq(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp ueq float [[Y]], 2.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[FADD]], float [[X]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp ueq float %y, 2.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %fadd, float %x
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_one(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_one(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp one float [[Y]], 2.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[X]], float [[FADD]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp one float %y, 2.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %x, float %fadd
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_oeq_zero(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_oeq_zero(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp oeq float [[Y]], 0.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[FADD]], float [[X]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp oeq float %y, 0.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %fadd, float %x
+  ret float %retval
+}
+
+define float @select_fcmp_fadd_une_zero(float %x, float %y) {
+; CHECK-LABEL: define float @select_fcmp_fadd_une_zero(
+; CHECK-SAME: float [[X:%.*]], float [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp une float [[Y]], 0.000000e+00
+; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[FCMP]], float [[X]], float [[FADD]]
+; CHECK-NEXT:    ret float [[RETVAL]]
+;
+  %fcmp = fcmp une float %y, 0.0
+  %fadd = fadd float %x, %y
+  %retval = select i1 %fcmp, float %x, float %fadd
+  ret float %retval
+}
+
+define <2 x float> @select_fcmp_fadd_oeq_not_zero_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_oeq_not_zero_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp oeq <2 x float> [[Y]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[FADD]], <2 x float> [[X]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp oeq <2 x float> %y, <float 2.0, float 2.0>
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %fadd, <2 x float> %x
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_une_not_zero_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_une_not_zero_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp une <2 x float> [[Y]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[X]], <2 x float> [[FADD]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp une <2 x float> %y, <float 2.0, float 2.0>
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %x, <2 x float> %fadd
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_ueq_nnan_not_zero_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_ueq_nnan_not_zero_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp nnan ueq <2 x float> [[Y]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[FADD]], <2 x float> [[X]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp nnan ueq <2 x float> %y, <float 2.0, float 2.0>
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %fadd, <2 x float> %x
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_one_nnan_not_zero_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_one_nnan_not_zero_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp nnan one <2 x float> [[Y]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[X]], <2 x float> [[FADD]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp nnan one <2 x float> %y, <float 2.0, float 2.0>
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %x, <2 x float> %fadd
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_ueq_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_ueq_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp ueq <2 x float> [[Y]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[FADD]], <2 x float> [[X]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp ueq <2 x float> %y, <float 2.0, float 2.0>
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %fadd, <2 x float> %x
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_one_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_one_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp one <2 x float> [[Y]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[X]], <2 x float> [[FADD]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp one <2 x float> %y, <float 2.0, float 2.0>
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %x, <2 x float> %fadd
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_oeq_zero_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_oeq_zero_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp oeq <2 x float> [[Y]], zeroinitializer
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[FADD]], <2 x float> [[X]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp oeq <2 x float> %y, zeroinitializer
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %fadd, <2 x float> %x
+  ret <2 x float> %retval
+}
+
+define <2 x float> @select_fcmp_fadd_une_zero_vec(<2 x float> %x, <2 x float> %y) {
+; CHECK-LABEL: define <2 x float> @select_fcmp_fadd_une_zero_vec(
+; CHECK-SAME: <2 x float> [[X:%.*]], <2 x float> [[Y:%.*]]) {
+; CHECK-NEXT:    [[FCMP:%.*]] = fcmp une <2 x float> [[Y]], zeroinitializer
+; CHECK-NEXT:    [[FADD:%.*]] = fadd <2 x float> [[X]], [[Y]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[FCMP]], <2 x float> [[X]], <2 x float> [[FADD]]
+; CHECK-NEXT:    ret <2 x float> [[RETVAL]]
+;
+  %fcmp = fcmp une <2 x float> %y, zeroinitializer
+  %fadd = fadd <2 x float> %x, %y
+  %retval = select <2 x i1> %fcmp, <2 x float> %x, <2 x float> %fadd
+  ret <2 x float> %retval
+}

>From 866830eb6584e33df41e0ef4db635470b6ad5358 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Thu, 10 Oct 2024 20:09:09 +0100
Subject: [PATCH 2/2] InstCombine: extend select-equiv to support vectors

foldSelectEquivalence currently doesn't support comparisons on vector
types due to correctness concerns. Note that the only concern is
lane-crossing; ShuffleVector is the only possible lane-crossing
instruction, and ShuffleVectorInst::{isIdentity,isShuffle} are the exact
properties that should not be broken for valid vector-replacements. Put
in the checks, and lift the limitation.
---
 llvm/lib/Analysis/ValueTracking.cpp                    |  4 +++-
 llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp  |  7 +++++--
 llvm/test/Transforms/InstCombine/and-or-icmps.ll       |  2 +-
 llvm/test/Transforms/InstCombine/select-binop-cmp.ll   | 10 +++++-----
 .../Transforms/InstCombine/select-value-equivalence.ll |  6 +++---
 5 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index f83347e7cd2bba..c71d17011d7a0d 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -6950,7 +6950,9 @@ bool llvm::onlyUsedByLifetimeMarkersOrDroppableInsts(const Value *V) {
 bool llvm::isNotCrossLaneOperation(const Instruction *I) {
   if (auto *II = dyn_cast<IntrinsicInst>(I))
     return isTriviallyVectorizable(II->getIntrinsicID());
-  return !isa<CallBase, BitCastInst, ShuffleVectorInst, ExtractElementInst>(I);
+  auto *Shuffle = dyn_cast<ShuffleVectorInst>(I);
+  return (!Shuffle || Shuffle->isSelect()) &&
+         !isa<CallBase, BitCastInst, ExtractElementInst>(I);
 }
 
 bool llvm::isSafeToSpeculativelyExecute(const Instruction *Inst,
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
index 358563a5fcd537..820d3608c8dc49 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -1288,6 +1288,10 @@ bool InstCombinerImpl::replaceInInstruction(Value *V, Value *Old, Value *New,
       !isSafeToSpeculativelyExecuteWithVariableReplaced(I))
     return false;
 
+  // Forbid potentially lane-crossing instructions.
+  if (Old->getType()->isVectorTy() && !isNotCrossLaneOperation(I))
+    return false;
+
   bool Changed = false;
   for (Use &U : I->operands()) {
     if (U == Old) {
@@ -1366,9 +1370,8 @@ Instruction *InstCombinerImpl::foldSelectValueEquivalence(SelectInst &Sel,
     // with different operands, which should not cause side-effects or trigger
     // undefined behavior). Only do this if CmpRHS is a constant, as
     // profitability is not clear for other cases.
-    // FIXME: Support vectors.
     if (OldOp == CmpLHS && match(NewOp, m_ImmConstant()) &&
-        !match(OldOp, m_Constant()) && !Cmp.getType()->isVectorTy() &&
+        !match(OldOp, m_Constant()) &&
         isGuaranteedNotToBeUndef(NewOp, SQ.AC, &Sel, &DT))
       if (replaceInInstruction(TrueVal, OldOp, NewOp))
         return &Sel;
diff --git a/llvm/test/Transforms/InstCombine/and-or-icmps.ll b/llvm/test/Transforms/InstCombine/and-or-icmps.ll
index ad28ad980de5b4..eb4723c86542de 100644
--- a/llvm/test/Transforms/InstCombine/and-or-icmps.ll
+++ b/llvm/test/Transforms/InstCombine/and-or-icmps.ll
@@ -983,7 +983,7 @@ define <2 x i1> @substitute_constant_or_ne_slt_swap_vec_poison(<2 x i8> %x, <2 x
 define <2 x i1> @substitute_constant_or_ne_slt_swap_vec_logical(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-LABEL: @substitute_constant_or_ne_slt_swap_vec_logical(
 ; CHECK-NEXT:    [[C1:%.*]] = icmp ne <2 x i8> [[X:%.*]], <i8 42, i8 poison>
-; CHECK-NEXT:    [[C2:%.*]] = icmp slt <2 x i8> [[Y:%.*]], [[X]]
+; CHECK-NEXT:    [[C2:%.*]] = icmp slt <2 x i8> [[Y:%.*]], <i8 42, i8 poison>
 ; CHECK-NEXT:    [[R:%.*]] = select <2 x i1> [[C1]], <2 x i1> <i1 true, i1 true>, <2 x i1> [[C2]]
 ; CHECK-NEXT:    ret <2 x i1> [[R]]
 ;
diff --git a/llvm/test/Transforms/InstCombine/select-binop-cmp.ll b/llvm/test/Transforms/InstCombine/select-binop-cmp.ll
index 647287ef5ebad1..cd8c29ba4cd819 100644
--- a/llvm/test/Transforms/InstCombine/select-binop-cmp.ll
+++ b/llvm/test/Transforms/InstCombine/select-binop-cmp.ll
@@ -552,12 +552,12 @@ define i32 @select_xor_icmp_bad_6(i32 %x, i32 %y, i32 %z) {
   ret i32 %C
 }
 
-; Value equivalence substitution is all-or-nothing, so needs a scalar compare.
+; Value equivalence substitution is valid.
 
-define <2 x i8> @select_xor_icmp_vec_bad(<2 x i8> %x, <2 x i8> %y, <2 x i8> %z) {
-; CHECK-LABEL: @select_xor_icmp_vec_bad(
+define <2 x i8> @select_xor_icmp_vec_equivalence(<2 x i8> %x, <2 x i8> %y, <2 x i8> %z) {
+; CHECK-LABEL: @select_xor_icmp_vec_equivalence(
 ; CHECK-NEXT:    [[A:%.*]] = icmp eq <2 x i8> [[X:%.*]], <i8 5, i8 3>
-; CHECK-NEXT:    [[B:%.*]] = xor <2 x i8> [[X]], [[Z:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = xor <2 x i8> [[Z:%.*]], <i8 5, i8 3>
 ; CHECK-NEXT:    [[C:%.*]] = select <2 x i1> [[A]], <2 x i8> [[B]], <2 x i8> [[Y:%.*]]
 ; CHECK-NEXT:    ret <2 x i8> [[C]]
 ;
@@ -567,7 +567,7 @@ define <2 x i8> @select_xor_icmp_vec_bad(<2 x i8> %x, <2 x i8> %y, <2 x i8> %z)
   ret <2 x i8>  %C
 }
 
-; Value equivalence substitution is all-or-nothing, so needs a scalar compare.
+; Value equivalence substitution is invalid due to lane-crossing shufflevector.
 
 define <2 x i32> @vec_select_no_equivalence(<2 x i32> %x) {
 ; CHECK-LABEL: @vec_select_no_equivalence(
diff --git a/llvm/test/Transforms/InstCombine/select-value-equivalence.ll b/llvm/test/Transforms/InstCombine/select-value-equivalence.ll
index 62c8a2c981c5b0..ba389821cd1529 100644
--- a/llvm/test/Transforms/InstCombine/select-value-equivalence.ll
+++ b/llvm/test/Transforms/InstCombine/select-value-equivalence.ll
@@ -5,7 +5,7 @@ define <2 x i8> @select_icmp_insertelement_eq(<2 x i8> %x, <2 x i8> %y, i8 %i) {
 ; CHECK-LABEL: define <2 x i8> @select_icmp_insertelement_eq(
 ; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], i8 [[I:%.*]]) {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
-; CHECK-NEXT:    [[INSERT:%.*]] = insertelement <2 x i8> [[Y]], i8 0, i8 [[I]]
+; CHECK-NEXT:    [[INSERT:%.*]] = insertelement <2 x i8> <i8 2, i8 2>, i8 0, i8 [[I]]
 ; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP]], <2 x i8> [[INSERT]], <2 x i8> [[X]]
 ; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
 ;
@@ -19,7 +19,7 @@ define <2 x i8> @select_icmp_insertelement_ne(<2 x i8> %x, <2 x i8> %y, i8 %i) {
 ; CHECK-LABEL: define <2 x i8> @select_icmp_insertelement_ne(
 ; CHECK-SAME: <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], i8 [[I:%.*]]) {
 ; CHECK-NEXT:    [[CMP_NOT:%.*]] = icmp eq <2 x i8> [[Y]], <i8 2, i8 2>
-; CHECK-NEXT:    [[INSERT:%.*]] = insertelement <2 x i8> [[Y]], i8 0, i8 [[I]]
+; CHECK-NEXT:    [[INSERT:%.*]] = insertelement <2 x i8> <i8 2, i8 2>, i8 0, i8 [[I]]
 ; CHECK-NEXT:    [[RETVAL:%.*]] = select <2 x i1> [[CMP_NOT]], <2 x i8> [[INSERT]], <2 x i8> [[X]]
 ; CHECK-NEXT:    ret <2 x i8> [[RETVAL]]
 ;
@@ -46,7 +46,7 @@ define <4 x i8> @select_icmp_shufflevector_select(<4 x i8> %x, <4 x i8> %y, <4 x
 ; CHECK-LABEL: define <4 x i8> @select_icmp_shufflevector_select(
 ; CHECK-SAME: <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <4 x i8> [[Z:%.*]]) {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <4 x i8> [[Y]], <i8 2, i8 2, i8 2, i8 2>
-; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <4 x i8> [[Z]], <4 x i8> [[Y]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <4 x i8> [[Z]], <4 x i8> <i8 poison, i8 2, i8 poison, i8 2>, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
 ; CHECK-NEXT:    [[RETVAL:%.*]] = select <4 x i1> [[CMP]], <4 x i8> [[SHUFFLE]], <4 x i8> [[X]]
 ; CHECK-NEXT:    ret <4 x i8> [[RETVAL]]
 ;



More information about the llvm-commits mailing list