From bfc9a5f7d3fda13dc9545a22c23e4e16834ac9e2 Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@gmail.com>
Date: Sun, 15 Apr 2012 22:43:31 +0000
Subject: [PATCH] Remove AVX2 vpermq and vpermpd intrinsics. These can now be
 handled with normal shuffle vectors.

llvm-svn: 154778
---
 llvm/include/llvm/IntrinsicsX86.td           |  6 -----
 llvm/lib/Target/X86/X86InstrSSE.td           | 25 +++++++-------------
 llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll | 16 -------------
 3 files changed, 8 insertions(+), 39 deletions(-)

diff --git a/llvm/include/llvm/IntrinsicsX86.td b/llvm/include/llvm/IntrinsicsX86.td
index a6fda4a3afc7..a73337330c35 100644
--- a/llvm/include/llvm/IntrinsicsX86.td
+++ b/llvm/include/llvm/IntrinsicsX86.td
@@ -1659,15 +1659,9 @@ let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
   def int_x86_avx2_permd : GCCBuiltin<"__builtin_ia32_permvarsi256">,
               Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty, llvm_v8i32_ty],
                         [IntrNoMem]>;
-  def int_x86_avx2_permq : GCCBuiltin<"__builtin_ia32_permdi256">,
-              Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty, llvm_i8_ty],
-                        [IntrNoMem]>;
   def int_x86_avx2_permps : GCCBuiltin<"__builtin_ia32_permvarsf256">,
               Intrinsic<[llvm_v8f32_ty], [llvm_v8f32_ty, llvm_v8f32_ty],
                         [IntrNoMem]>;
-  def int_x86_avx2_permpd : GCCBuiltin<"__builtin_ia32_permdf256">,
-              Intrinsic<[llvm_v4f64_ty], [llvm_v4f64_ty, llvm_i8_ty],
-                        [IntrNoMem]>;
   def int_x86_avx2_vperm2i128 : GCCBuiltin<"__builtin_ia32_permti256">,
               Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
                          llvm_v4i64_ty, llvm_i8_ty], [IntrNoMem]>;
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index b0aeb3f5249f..8ce974d6fa7b 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -7755,24 +7755,26 @@ let ExeDomain = SSEPackedSingle in
 defm VPERMPS : avx2_perm<0x16, "vpermps", memopv8f32, int_x86_avx2_permps>;
 
 multiclass avx2_perm_imm<bits<8> opc, string OpcodeStr, PatFrag mem_frag,
-                         Intrinsic Int> {
+                         SDNode OpNode, ValueType OpVT> {
   def Yri : AVX2AIi8<opc, MRMSrcReg, (outs VR256:$dst),
                      (ins VR256:$src1, i8imm:$src2),
                      !strconcat(OpcodeStr,
                          "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
-                     [(set VR256:$dst, (Int VR256:$src1, imm:$src2))]>, VEX;
+                     [(set VR256:$dst,
+                       (OpVT (OpNode VR256:$src1, (i8 imm:$src2))))]>, VEX;
   def Ymi : AVX2AIi8<opc, MRMSrcMem, (outs VR256:$dst),
                      (ins i256mem:$src1, i8imm:$src2),
                      !strconcat(OpcodeStr,
                          "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
-                     [(set VR256:$dst, (Int (mem_frag addr:$src1), imm:$src2))]>,
+                     [(set VR256:$dst,
+                       (OpVT (OpNode (mem_frag addr:$src1), (i8 imm:$src2))))]>,
                      VEX;
 }
 
-defm VPERMQ : avx2_perm_imm<0x00, "vpermq", memopv4i64, int_x86_avx2_permq>,
+defm VPERMQ : avx2_perm_imm<0x00, "vpermq", memopv4i64, X86VPermq, v4i64>,
                             VEX_W;
 let ExeDomain = SSEPackedDouble in
-defm VPERMPD : avx2_perm_imm<0x01, "vpermpd", memopv4f64, int_x86_avx2_permpd>,
+defm VPERMPD : avx2_perm_imm<0x01, "vpermpd", memopv4f64, X86VPermpd, v4f64>,
                              VEX_W;
 
 let Predicates = [HasAVX2] in {
@@ -7780,22 +7782,11 @@ def : Pat<(v8i32 (X86VPermd VR256:$src1, VR256:$src2)),
           (VPERMDYrr VR256:$src1, VR256:$src2)>;
 def : Pat<(v8f32 (X86VPermps VR256:$src1, VR256:$src2)),
           (VPERMPSYrr VR256:$src1, VR256:$src2)>;
-          
-def : Pat<(v4i64 (X86VPermq VR256:$src1, (i8 imm:$imm))),
-          (VPERMQYri VR256:$src1, imm:$imm)>;
-def : Pat<(v4f64 (X86VPermpd VR256:$src1, (i8 imm:$imm))),
-          (VPERMPDYri VR256:$src1, imm:$imm)>;
 
-def : Pat<(v8i32 (X86VPermps VR256:$src1, (bc_v8i32 (memopv4i64 addr:$src2)))),
+def : Pat<(v8i32 (X86VPermd VR256:$src1, (bc_v8i32 (memopv4i64 addr:$src2)))),
           (VPERMDYrm VR256:$src1, addr:$src2)>;
 def : Pat<(v8f32 (X86VPermps VR256:$src1, (memopv8f32 addr:$src2))),
           (VPERMPSYrm VR256:$src1, addr:$src2)>;
-          
-def : Pat<(v4i64 (X86VPermq (memopv4i64 addr:$src1), (i8 imm:$imm))),
-          (VPERMQYmi addr:$src1, imm:$imm)>;
-def : Pat<(v4f64 (X86VPermpd (memopv4f64 addr:$src1), (i8 imm:$imm))),
-          (VPERMPDYmi addr:$src1, imm:$imm)>;
-
 }
 
 //===----------------------------------------------------------------------===//
diff --git a/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll b/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
index 1fb41c02b9e9..3f27a0291b4f 100644
--- a/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
+++ b/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
@@ -800,22 +800,6 @@ define <8 x float> @test_x86_avx2_permps(<8 x float> %a0, <8 x float> %a1) {
 declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x float>) nounwind readonly
 
 
-define <4 x i64> @test_x86_avx2_permq(<4 x i64> %a0) {
-  ; CHECK: vpermq
-  %res = call <4 x i64> @llvm.x86.avx2.permq(<4 x i64> %a0, i8 7) ; <<4 x i64>> [#uses=1]
-  ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.permq(<4 x i64>, i8) nounwind readonly
-
-
-define <4 x double> @test_x86_avx2_permpd(<4 x double> %a0) {
-  ; CHECK: vpermpd
-  %res = call <4 x double> @llvm.x86.avx2.permpd(<4 x double> %a0, i8 7) ; <<4 x double>> [#uses=1]
-  ret <4 x double> %res
-}
-declare <4 x double> @llvm.x86.avx2.permpd(<4 x double>, i8) nounwind readonly
-
-
 define <4 x i64> @test_x86_avx2_vperm2i128(<4 x i64> %a0, <4 x i64> %a1) {
   ; CHECK: vperm2i128
   %res = call <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64> %a0, <4 x i64> %a1, i8 1) ; <<4 x i64>> [#uses=1]