[llvm] 22e4203 - [PowerPC][NFC] Pre-commit case for lowering vector shuffles to xxsplti32dx (64 bit)

[Amy Kwan via llvm-commits]

Author: Amy Kwan
Date: 2022-10-14T10:15:34-05:00
New Revision: 22e4203df813a8051b40adb3e2872e30fdbe1bbe

URL: https://github.com/llvm/llvm-project/commit/22e4203df813a8051b40adb3e2872e30fdbe1bbe
DIFF: https://github.com/llvm/llvm-project/commit/22e4203df813a8051b40adb3e2872e30fdbe1bbe.diff

LOG: [PowerPC][NFC] Pre-commit case for lowering vector shuffles to xxsplti32dx (64 bit)

This patch adds a test case for lowering vector shuffles to xxsplti32dx in
preparation for D135024. The test case added in this patch only adds the
64-bit CHECKs, as the 32-bit CHECKs cannot be generated (in which D135024
aims to fix).

Added: 
    llvm/test/CodeGen/PowerPC/p10-splatImm32-undef.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/PowerPC/p10-splatImm32-undef.ll b/llvm/test/CodeGen/PowerPC/p10-splatImm32-undef.ll
new file mode 100644
index 0000000000000..2292c67f7d864
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/p10-splatImm32-undef.ll
@@ -0,0 +1,77 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
+; RUN:     -ppc-asm-full-reg-names -mcpu=pwr10 < %s | \
+; RUN:     FileCheck %s --check-prefix=CHECK-LINUX
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
+; RUN:     -ppc-asm-full-reg-names -mcpu=pwr10 < %s | \
+; RUN:     FileCheck %s --check-prefix=CHECK-LINUX-BE
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64-ibm-aix-xcoff \
+; RUN:     -ppc-asm-full-reg-names -mcpu=pwr10 < %s | \
+; RUN:     FileCheck %s --check-prefix=CHECK-AIX
+
+declare hidden i32 @call1()
+define hidden void @function1() {
+; CHECK-LINUX-LABEL: function1:
+; CHECK-LINUX:       # %bb.0: # %entry
+; CHECK-LINUX-NEXT:    mflr r0
+; CHECK-LINUX-NEXT:    std r0, 16(r1)
+; CHECK-LINUX-NEXT:    stdu r1, -32(r1)
+; CHECK-LINUX-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-LINUX-NEXT:    .cfi_offset lr, 16
+; CHECK-LINUX-NEXT:    bl call1 at notoc
+; CHECK-LINUX-NEXT:    addi r1, r1, 32
+; CHECK-LINUX-NEXT:    ld r0, 16(r1)
+; CHECK-LINUX-NEXT:    mtlr r0
+; CHECK-LINUX-NEXT:    blr
+;
+; CHECK-LINUX-BE-LABEL: function1:
+; CHECK-LINUX-BE:       # %bb.0: # %entry
+; CHECK-LINUX-BE-NEXT:    mflr r0
+; CHECK-LINUX-BE-NEXT:    std r0, 16(r1)
+; CHECK-LINUX-BE-NEXT:    stdu r1, -112(r1)
+; CHECK-LINUX-BE-NEXT:    .cfi_def_cfa_offset 112
+; CHECK-LINUX-BE-NEXT:    .cfi_offset lr, 16
+; CHECK-LINUX-BE-NEXT:    bl call1
+; CHECK-LINUX-BE-NEXT:    nop
+; CHECK-LINUX-BE-NEXT:    addi r1, r1, 112
+; CHECK-LINUX-BE-NEXT:    ld r0, 16(r1)
+; CHECK-LINUX-BE-NEXT:    mtlr r0
+; CHECK-LINUX-BE-NEXT:    blr
+;
+; CHECK-AIX-LABEL: function1:
+; CHECK-AIX:       # %bb.0: # %entry
+; CHECK-AIX-NEXT:    mflr r0
+; CHECK-AIX-NEXT:    std r0, 16(r1)
+; CHECK-AIX-NEXT:    stdu r1, -112(r1)
+; CHECK-AIX-NEXT:    bl .call1[PR]
+; CHECK-AIX-NEXT:    nop
+; CHECK-AIX-NEXT:    addi r1, r1, 112
+; CHECK-AIX-NEXT:    ld r0, 16(r1)
+; CHECK-AIX-NEXT:    mtlr r0
+; CHECK-AIX-NEXT:    blr
+entry:
+  %tailcall1 = tail call i32 @call1()
+  %0 = insertelement <4 x i32> poison, i32 %tailcall1, i64 1
+  %1 = insertelement <4 x i32> %0, i32 0, i64 2
+  %2 = insertelement <4 x i32> %1, i32 0, i64 3
+  %3 = trunc <4 x i32> %2 to <4 x i8>
+  %4 = icmp eq <4 x i8> %3, zeroinitializer
+  %5 = shufflevector <4 x i1> %4, <4 x i1> poison, <2 x i32> <i32 3, i32 undef>
+  %6 = shufflevector <4 x i1> %4, <4 x i1> poison, <2 x i32> <i32 2, i32 undef>
+  %7 = xor <2 x i1> %5, <i1 true, i1 poison>
+  %8 = shufflevector <2 x i1> %7, <2 x i1> poison, <2 x i32> zeroinitializer
+  %9 = zext <2 x i1> %8 to <2 x i64>
+  %10 = xor <2 x i1> %6, <i1 true, i1 poison>
+  %11 = shufflevector <2 x i1> %10, <2 x i1> poison, <2 x i32> zeroinitializer
+  %12 = zext <2 x i1> %11 to <2 x i64>
+  br label %next_block
+
+next_block:
+  %13 = add <2 x i64> zeroinitializer, %9
+  %14 = add <2 x i64> zeroinitializer, %12
+  %shift704 = shufflevector <2 x i64> %13, <2 x i64> poison, <2 x i32> <i32 1, i32 undef>
+  %15 = add <2 x i64> %shift704, %13
+  %shift705 = shufflevector <2 x i64> %14, <2 x i64> poison, <2 x i32> <i32 1, i32 undef>
+  %16 = add <2 x i64> %shift705, %14
+  ret void
+}