[llvm] Reland "VectorUtils: mark xrint as trivially vectorizable" (PR #71416)
Ramkumar Ramachandra via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 6 08:52:28 PST 2023
https://github.com/artagnon created https://github.com/llvm/llvm-project/pull/71416
With the recent change 98c90a13 (ISel: introduce vector ISD::LRINT, ISD::LLRINT; custom RISCV lowering), it is now possible for SLPVectorizer, LoopVectorize, and Scalarizer to operate on llvm.lrint and llvm.llrint, with vector codegen for the RISC-V target. Make a trivial change to VectorUtils, and update the corresponding tests.
A couple of important fixes have been landed since the original patch was landed and reverted, and it is now safe to re-land the patch: 5e1d81a (LegalizeIntegerTypes: implement PromoteIntRes for xrint) and fd887a3 (LegalizeVectorTypes: fix bug in widening of vec result in xrint). See also #71399, which proves that lrint and llrint will indeed produce vector codegen on RISC-V.
Fixes #55208.
>From 3d1e74f18e3a638b21c84cd7a8e4ed3747b6c543 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <Ramkumar.Ramachandra at imgtec.com>
Date: Tue, 31 Oct 2023 21:29:15 +0000
Subject: [PATCH] Reland "VectorUtils: mark xrint as trivially vectorizable"
With the recent change 98c90a13 (ISel: introduce vector ISD::LRINT,
ISD::LLRINT; custom RISCV lowering), it is now possible for
SLPVectorizer, LoopVectorize, and Scalarizer to operate on llvm.lrint
and llvm.llrint, with vector codegen for the RISC-V target. Make a
trivial change to VectorUtils, and update the corresponding tests.
A couple of important fixes have been landed since the original patch
was landed and reverted, and it is now safe to re-land the patch:
5e1d81a (LegalizeIntegerTypes: implement PromoteIntRes for xrint) and
fd887a3 (LegalizeVectorTypes: fix bug in widening of vec result in
xrint). See also #71399 which proves that lrint and llrint will indeed
produce vector codegen on RISC-V.
Fixes #55208.
---
llvm/lib/Analysis/VectorUtils.cpp | 4 +
.../Transforms/LoopVectorize/intrinsic.ll | 4 +-
.../Transforms/SLPVectorizer/RISCV/fround.ll | 165 ++++--------------
llvm/test/Transforms/Scalarizer/intrinsics.ll | 14 +-
4 files changed, 48 insertions(+), 139 deletions(-)
diff --git a/llvm/lib/Analysis/VectorUtils.cpp b/llvm/lib/Analysis/VectorUtils.cpp
index be171867a2bf4d9..4f5db8b7aaf746f 100644
--- a/llvm/lib/Analysis/VectorUtils.cpp
+++ b/llvm/lib/Analysis/VectorUtils.cpp
@@ -91,6 +91,8 @@ bool llvm::isTriviallyVectorizable(Intrinsic::ID ID) {
case Intrinsic::canonicalize:
case Intrinsic::fptosi_sat:
case Intrinsic::fptoui_sat:
+ case Intrinsic::lrint:
+ case Intrinsic::llrint:
return true;
default:
return false;
@@ -122,6 +124,8 @@ bool llvm::isVectorIntrinsicWithOverloadTypeAtArg(Intrinsic::ID ID,
switch (ID) {
case Intrinsic::fptosi_sat:
case Intrinsic::fptoui_sat:
+ case Intrinsic::lrint:
+ case Intrinsic::llrint:
return OpdIdx == -1 || OpdIdx == 0;
case Intrinsic::is_fpclass:
return OpdIdx == 0;
diff --git a/llvm/test/Transforms/LoopVectorize/intrinsic.ll b/llvm/test/Transforms/LoopVectorize/intrinsic.ll
index 3e7754951de6a83..0f070347dd4efb6 100644
--- a/llvm/test/Transforms/LoopVectorize/intrinsic.ll
+++ b/llvm/test/Transforms/LoopVectorize/intrinsic.ll
@@ -1602,7 +1602,7 @@ declare i32 @llvm.lrint.i32.f32(float)
define void @lrint_i32_f32(ptr %x, ptr %y, i64 %n) {
; CHECK-LABEL: @lrint_i32_f32(
-; CHECK-NOT: llvm.lrint.v4i32.v4f32
+; CHECK: llvm.lrint.v4i32.v4f32
; CHECK: ret void
;
entry:
@@ -1628,7 +1628,7 @@ declare i64 @llvm.llrint.i64.f32(float)
define void @llrint_i64_f32(ptr %x, ptr %y, i64 %n) {
; CHECK-LABEL: @llrint_i64_f32(
-; CHECK-NOT: llvm.llrint.v4i32.v4f32
+; CHECK: llvm.llrint.v4i64.v4f32
; CHECK: ret void
;
entry:
diff --git a/llvm/test/Transforms/SLPVectorizer/RISCV/fround.ll b/llvm/test/Transforms/SLPVectorizer/RISCV/fround.ll
index e5c46b72a1c30fc..9cd0d5d321e2f60 100644
--- a/llvm/test/Transforms/SLPVectorizer/RISCV/fround.ll
+++ b/llvm/test/Transforms/SLPVectorizer/RISCV/fround.ll
@@ -34,13 +34,8 @@ define <2 x i32> @lrint_v2i32f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr [[A]], align 8
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i32 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <2 x i32> undef, i32 [[TMP1]], i32 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <2 x i32> [[VECINS]], i32 [[TMP2]], i32 1
-; CHECK-NEXT: ret <2 x i32> [[VECINS_1]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <2 x i32> @llvm.lrint.v2i32.v2f32(<2 x float> [[TMP0]])
+; CHECK-NEXT: ret <2 x i32> [[TMP1]]
;
entry:
%0 = load <2 x float>, ptr %a
@@ -58,19 +53,8 @@ define <4 x i32> @lrint_v4i32f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A]], align 16
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <4 x i32> undef, i32 [[TMP1]], i32 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <4 x i32> [[VECINS]], i32 [[TMP2]], i32 1
-; CHECK-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
-; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_2]])
-; CHECK-NEXT: [[VECINS_2:%.*]] = insertelement <4 x i32> [[VECINS_1]], i32 [[TMP3]], i32 2
-; CHECK-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
-; CHECK-NEXT: [[TMP4:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_3]])
-; CHECK-NEXT: [[VECINS_3:%.*]] = insertelement <4 x i32> [[VECINS_2]], i32 [[TMP4]], i32 3
-; CHECK-NEXT: ret <4 x i32> [[VECINS_3]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i32> @llvm.lrint.v4i32.v4f32(<4 x float> [[TMP0]])
+; CHECK-NEXT: ret <4 x i32> [[TMP1]]
;
entry:
%0 = load <4 x float>, ptr %a
@@ -94,31 +78,8 @@ define <8 x i32> @lrint_v8i32f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[A]], align 32
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <8 x float> [[TMP0]], i32 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <8 x i32> undef, i32 [[TMP1]], i32 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <8 x float> [[TMP0]], i32 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <8 x i32> [[VECINS]], i32 [[TMP2]], i32 1
-; CHECK-NEXT: [[VECEXT_2:%.*]] = extractelement <8 x float> [[TMP0]], i32 2
-; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_2]])
-; CHECK-NEXT: [[VECINS_2:%.*]] = insertelement <8 x i32> [[VECINS_1]], i32 [[TMP3]], i32 2
-; CHECK-NEXT: [[VECEXT_3:%.*]] = extractelement <8 x float> [[TMP0]], i32 3
-; CHECK-NEXT: [[TMP4:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_3]])
-; CHECK-NEXT: [[VECINS_3:%.*]] = insertelement <8 x i32> [[VECINS_2]], i32 [[TMP4]], i32 3
-; CHECK-NEXT: [[VECEXT_4:%.*]] = extractelement <8 x float> [[TMP0]], i32 4
-; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_4]])
-; CHECK-NEXT: [[VECINS_4:%.*]] = insertelement <8 x i32> [[VECINS_3]], i32 [[TMP5]], i32 4
-; CHECK-NEXT: [[VECEXT_5:%.*]] = extractelement <8 x float> [[TMP0]], i32 5
-; CHECK-NEXT: [[TMP6:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_5]])
-; CHECK-NEXT: [[VECINS_5:%.*]] = insertelement <8 x i32> [[VECINS_4]], i32 [[TMP6]], i32 5
-; CHECK-NEXT: [[VECEXT_6:%.*]] = extractelement <8 x float> [[TMP0]], i32 6
-; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_6]])
-; CHECK-NEXT: [[VECINS_6:%.*]] = insertelement <8 x i32> [[VECINS_5]], i32 [[TMP7]], i32 6
-; CHECK-NEXT: [[VECEXT_7:%.*]] = extractelement <8 x float> [[TMP0]], i32 7
-; CHECK-NEXT: [[TMP8:%.*]] = call i32 @llvm.lrint.i32.f32(float [[VECEXT_7]])
-; CHECK-NEXT: [[VECINS_7:%.*]] = insertelement <8 x i32> [[VECINS_6]], i32 [[TMP8]], i32 7
-; CHECK-NEXT: ret <8 x i32> [[VECINS_7]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <8 x i32> @llvm.lrint.v8i32.v8f32(<8 x float> [[TMP0]])
+; CHECK-NEXT: ret <8 x i32> [[TMP1]]
;
entry:
%0 = load <8 x float>, ptr %a
@@ -154,13 +115,8 @@ define <2 x i64> @lrint_v2i64f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr [[A]], align 8
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i64 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <2 x i64> undef, i64 [[TMP1]], i64 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i64 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <2 x i64> [[VECINS]], i64 [[TMP2]], i64 1
-; CHECK-NEXT: ret <2 x i64> [[VECINS_1]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <2 x i64> @llvm.lrint.v2i64.v2f32(<2 x float> [[TMP0]])
+; CHECK-NEXT: ret <2 x i64> [[TMP1]]
;
entry:
%0 = load <2 x float>, ptr %a
@@ -178,19 +134,8 @@ define <4 x i64> @lrint_v4i64f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A]], align 16
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i64 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <4 x i64> undef, i64 [[TMP1]], i64 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i64 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <4 x i64> [[VECINS]], i64 [[TMP2]], i64 1
-; CHECK-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i64 2
-; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_2]])
-; CHECK-NEXT: [[VECINS_2:%.*]] = insertelement <4 x i64> [[VECINS_1]], i64 [[TMP3]], i64 2
-; CHECK-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i64 3
-; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_3]])
-; CHECK-NEXT: [[VECINS_3:%.*]] = insertelement <4 x i64> [[VECINS_2]], i64 [[TMP4]], i64 3
-; CHECK-NEXT: ret <4 x i64> [[VECINS_3]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.lrint.v4i64.v4f32(<4 x float> [[TMP0]])
+; CHECK-NEXT: ret <4 x i64> [[TMP1]]
;
entry:
%0 = load <4 x float>, ptr %a
@@ -214,31 +159,14 @@ define <8 x i64> @lrint_v8i64f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[A]], align 32
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <8 x float> [[TMP0]], i64 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <8 x i64> undef, i64 [[TMP1]], i64 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <8 x float> [[TMP0]], i64 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <8 x i64> [[VECINS]], i64 [[TMP2]], i64 1
-; CHECK-NEXT: [[VECEXT_2:%.*]] = extractelement <8 x float> [[TMP0]], i64 2
-; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_2]])
-; CHECK-NEXT: [[VECINS_2:%.*]] = insertelement <8 x i64> [[VECINS_1]], i64 [[TMP3]], i64 2
-; CHECK-NEXT: [[VECEXT_3:%.*]] = extractelement <8 x float> [[TMP0]], i64 3
-; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_3]])
-; CHECK-NEXT: [[VECINS_3:%.*]] = insertelement <8 x i64> [[VECINS_2]], i64 [[TMP4]], i64 3
-; CHECK-NEXT: [[VECEXT_4:%.*]] = extractelement <8 x float> [[TMP0]], i64 4
-; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_4]])
-; CHECK-NEXT: [[VECINS_4:%.*]] = insertelement <8 x i64> [[VECINS_3]], i64 [[TMP5]], i64 4
-; CHECK-NEXT: [[VECEXT_5:%.*]] = extractelement <8 x float> [[TMP0]], i64 5
-; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_5]])
-; CHECK-NEXT: [[VECINS_5:%.*]] = insertelement <8 x i64> [[VECINS_4]], i64 [[TMP6]], i64 5
-; CHECK-NEXT: [[VECEXT_6:%.*]] = extractelement <8 x float> [[TMP0]], i64 6
-; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_6]])
-; CHECK-NEXT: [[VECINS_6:%.*]] = insertelement <8 x i64> [[VECINS_5]], i64 [[TMP7]], i64 6
-; CHECK-NEXT: [[VECEXT_7:%.*]] = extractelement <8 x float> [[TMP0]], i64 7
-; CHECK-NEXT: [[TMP8:%.*]] = call i64 @llvm.lrint.i64.f32(float [[VECEXT_7]])
-; CHECK-NEXT: [[VECINS_7:%.*]] = insertelement <8 x i64> [[VECINS_6]], i64 [[TMP8]], i64 7
-; CHECK-NEXT: ret <8 x i64> [[VECINS_7]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = call <4 x i64> @llvm.lrint.v4i64.v4f32(<4 x float> [[TMP1]])
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i64> [[TMP2]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i64> @llvm.lrint.v4i64.v4f32(<4 x float> [[TMP4]])
+; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i64> [[TMP5]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[VECINS_71:%.*]] = shufflevector <8 x i64> [[TMP3]], <8 x i64> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT: ret <8 x i64> [[VECINS_71]]
;
entry:
%0 = load <8 x float>, ptr %a
@@ -274,13 +202,8 @@ define <2 x i64> @llrint_v2i64f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr [[A]], align 8
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i64 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <2 x i64> undef, i64 [[TMP1]], i64 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i64 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <2 x i64> [[VECINS]], i64 [[TMP2]], i64 1
-; CHECK-NEXT: ret <2 x i64> [[VECINS_1]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <2 x i64> @llvm.llrint.v2i64.v2f32(<2 x float> [[TMP0]])
+; CHECK-NEXT: ret <2 x i64> [[TMP1]]
;
entry:
%0 = load <2 x float>, ptr %a
@@ -298,19 +221,8 @@ define <4 x i64> @llrint_v4i64f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A]], align 16
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i64 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <4 x i64> undef, i64 [[TMP1]], i64 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i64 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <4 x i64> [[VECINS]], i64 [[TMP2]], i64 1
-; CHECK-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i64 2
-; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_2]])
-; CHECK-NEXT: [[VECINS_2:%.*]] = insertelement <4 x i64> [[VECINS_1]], i64 [[TMP3]], i64 2
-; CHECK-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i64 3
-; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_3]])
-; CHECK-NEXT: [[VECINS_3:%.*]] = insertelement <4 x i64> [[VECINS_2]], i64 [[TMP4]], i64 3
-; CHECK-NEXT: ret <4 x i64> [[VECINS_3]]
+; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> [[TMP0]])
+; CHECK-NEXT: ret <4 x i64> [[TMP1]]
;
entry:
%0 = load <4 x float>, ptr %a
@@ -334,31 +246,14 @@ define <8 x i64> @llrint_v8i64f32(ptr %a) {
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x float>, ptr [[A]], align 32
-; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <8 x float> [[TMP0]], i64 0
-; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT]])
-; CHECK-NEXT: [[VECINS:%.*]] = insertelement <8 x i64> undef, i64 [[TMP1]], i64 0
-; CHECK-NEXT: [[VECEXT_1:%.*]] = extractelement <8 x float> [[TMP0]], i64 1
-; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_1]])
-; CHECK-NEXT: [[VECINS_1:%.*]] = insertelement <8 x i64> [[VECINS]], i64 [[TMP2]], i64 1
-; CHECK-NEXT: [[VECEXT_2:%.*]] = extractelement <8 x float> [[TMP0]], i64 2
-; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_2]])
-; CHECK-NEXT: [[VECINS_2:%.*]] = insertelement <8 x i64> [[VECINS_1]], i64 [[TMP3]], i64 2
-; CHECK-NEXT: [[VECEXT_3:%.*]] = extractelement <8 x float> [[TMP0]], i64 3
-; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_3]])
-; CHECK-NEXT: [[VECINS_3:%.*]] = insertelement <8 x i64> [[VECINS_2]], i64 [[TMP4]], i64 3
-; CHECK-NEXT: [[VECEXT_4:%.*]] = extractelement <8 x float> [[TMP0]], i64 4
-; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_4]])
-; CHECK-NEXT: [[VECINS_4:%.*]] = insertelement <8 x i64> [[VECINS_3]], i64 [[TMP5]], i64 4
-; CHECK-NEXT: [[VECEXT_5:%.*]] = extractelement <8 x float> [[TMP0]], i64 5
-; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_5]])
-; CHECK-NEXT: [[VECINS_5:%.*]] = insertelement <8 x i64> [[VECINS_4]], i64 [[TMP6]], i64 5
-; CHECK-NEXT: [[VECEXT_6:%.*]] = extractelement <8 x float> [[TMP0]], i64 6
-; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_6]])
-; CHECK-NEXT: [[VECINS_6:%.*]] = insertelement <8 x i64> [[VECINS_5]], i64 [[TMP7]], i64 6
-; CHECK-NEXT: [[VECEXT_7:%.*]] = extractelement <8 x float> [[TMP0]], i64 7
-; CHECK-NEXT: [[TMP8:%.*]] = call i64 @llvm.llrint.i64.f32(float [[VECEXT_7]])
-; CHECK-NEXT: [[VECINS_7:%.*]] = insertelement <8 x i64> [[VECINS_6]], i64 [[TMP8]], i64 7
-; CHECK-NEXT: ret <8 x i64> [[VECINS_7]]
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> [[TMP1]])
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i64> [[TMP2]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <8 x float> [[TMP0]], <8 x float> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> [[TMP4]])
+; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i64> [[TMP5]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[VECINS_71:%.*]] = shufflevector <8 x i64> [[TMP3]], <8 x i64> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT: ret <8 x i64> [[VECINS_71]]
;
entry:
%0 = load <8 x float>, ptr %a
diff --git a/llvm/test/Transforms/Scalarizer/intrinsics.ll b/llvm/test/Transforms/Scalarizer/intrinsics.ll
index f5e5be1f5998e00..cee44ef43426071 100644
--- a/llvm/test/Transforms/Scalarizer/intrinsics.ll
+++ b/llvm/test/Transforms/Scalarizer/intrinsics.ll
@@ -217,7 +217,12 @@ define <2 x i32> @scalarize_fptoui_sat(<2 x float> %x) #0 {
define <2 x i32> @scalarize_lrint(<2 x float> %x) #0 {
; CHECK-LABEL: @scalarize_lrint(
-; CHECK-NEXT: [[RND:%.*]] = call <2 x i32> @llvm.lrint.v2i32.v2f32(<2 x float> [[X:%.*]])
+; CHECK-NEXT: [[X_I0:%.*]] = extractelement <2 x float> [[X:%.*]], i64 0
+; CHECK-NEXT: [[RND_I0:%.*]] = call i32 @llvm.lrint.i32.f32(float [[X_I0]])
+; CHECK-NEXT: [[X_I1:%.*]] = extractelement <2 x float> [[X]], i64 1
+; CHECK-NEXT: [[RND_I1:%.*]] = call i32 @llvm.lrint.i32.f32(float [[X_I1]])
+; CHECK-NEXT: [[RND_UPTO0:%.*]] = insertelement <2 x i32> poison, i32 [[RND_I0]], i64 0
+; CHECK-NEXT: [[RND:%.*]] = insertelement <2 x i32> [[RND_UPTO0]], i32 [[RND_I1]], i64 1
; CHECK-NEXT: ret <2 x i32> [[RND]]
;
%rnd = call <2 x i32> @llvm.lrint.v2i32.v2f32(<2 x float> %x)
@@ -226,7 +231,12 @@ define <2 x i32> @scalarize_lrint(<2 x float> %x) #0 {
define <2 x i32> @scalarize_llrint(<2 x float> %x) #0 {
; CHECK-LABEL: @scalarize_llrint(
-; CHECK-NEXT: [[RND:%.*]] = call <2 x i32> @llvm.llrint.v2i32.v2f32(<2 x float> [[X:%.*]])
+; CHECK-NEXT: [[X_I0:%.*]] = extractelement <2 x float> [[X:%.*]], i64 0
+; CHECK-NEXT: [[RND_I0:%.*]] = call i32 @llvm.llrint.i32.f32(float [[X_I0]])
+; CHECK-NEXT: [[X_I1:%.*]] = extractelement <2 x float> [[X]], i64 1
+; CHECK-NEXT: [[RND_I1:%.*]] = call i32 @llvm.llrint.i32.f32(float [[X_I1]])
+; CHECK-NEXT: [[RND_UPTO0:%.*]] = insertelement <2 x i32> poison, i32 [[RND_I0]], i64 0
+; CHECK-NEXT: [[RND:%.*]] = insertelement <2 x i32> [[RND_UPTO0]], i32 [[RND_I1]], i64 1
; CHECK-NEXT: ret <2 x i32> [[RND]]
;
%rnd = call <2 x i32> @llvm.llrint.v2i32.v2f32(<2 x float> %x)
More information about the llvm-commits
mailing list