SelectionDAG: Use helper function to improve legalization of ISD::MUL

The TargetLowering::expandMUL() helper contains lowering code extracted
from the DAGTypeLegalizer and allows the SelectionDAGLegalizer to expand more
ISD::MUL patterns without having to use a library call.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206037 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index 20afb3d594286a9d5c05a0951bc300ba142468ad..230747c76bbf24b897dea4030dd80812c1daa916 100644 (file)
--- a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -3625,6 +3625,23 @@ void SelectionDAGLegalize::ExpandNode(SDNode *Node) {
                                     Node->getOperand(1)));
       break;
     }
+
+    SDValue Lo, Hi;
+    EVT HalfType = VT.getHalfSizedIntegerVT(*DAG.getContext());
+    if (TLI.isOperationLegalOrCustom(ISD::ZERO_EXTEND, VT) &&
+        TLI.isOperationLegalOrCustom(ISD::ANY_EXTEND, VT) &&
+        TLI.isOperationLegalOrCustom(ISD::SHL, VT) &&
+        TLI.isOperationLegalOrCustom(ISD::OR, VT) &&
+        TLI.expandMUL(Node, Lo, Hi, HalfType, DAG)) {
+      Lo = DAG.getNode(ISD::ZERO_EXTEND, dl, VT, Lo);
+      Hi = DAG.getNode(ISD::ANY_EXTEND, dl, VT, Hi);
+      SDValue Shift = DAG.getConstant(HalfType.getSizeInBits(),
+                                      TLI.getShiftAmountTy(HalfType));
+      Hi = DAG.getNode(ISD::SHL, dl, VT, Hi, Shift);
+      Results.push_back(DAG.getNode(ISD::OR, dl, VT, Lo, Hi));
+      break;
+    }
+
     Tmp1 = ExpandIntLibCall(Node, false,
                             RTLIB::MUL_I8,
                             RTLIB::MUL_I16, RTLIB::MUL_I32,

diff --git a/test/CodeGen/R600/mul.ll b/test/CodeGen/R600/mul.ll
index e1761485835ff4c92dffbd4299686a36fb8935ed..6ed754c5aa701139164121b0e61eb681cc62cc81 100644 (file)
--- a/test/CodeGen/R600/mul.ll
+++ b/test/CodeGen/R600/mul.ll
@@ -1,15 +1,14 @@
-; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK %s
-; RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI-CHECK %s
+; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG %s --check-prefix=FUNC
+; RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI --check-prefix=FUNC %s
 
 ; mul24 and mad24 are affected
 
-;EG-CHECK: @test2
-;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;FUNC-LABEL: @test2
+;EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-;SI-CHECK: @test2
-;SI-CHECK: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
-;SI-CHECK: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
+;SI: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
+;SI: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
 
 define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
   %b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
@@ -20,17 +19,16 @@ define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
   ret void
 }
 
-;EG-CHECK: @test4
-;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
-;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;FUNC-LABEL: @test4
+;EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
+;EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-;SI-CHECK: @test4
-;SI-CHECK: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
-;SI-CHECK: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
-;SI-CHECK: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
-;SI-CHECK: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
+;SI: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
+;SI: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
+;SI: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
+;SI: V_MUL_LO_I32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
 
 define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
   %b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
@@ -52,3 +50,32 @@ define void @trunc_i64_mul_to_i32(i32 addrspace(1)* %out, i64 %a, i64 %b) {
   store i32 %trunc, i32 addrspace(1)* %out, align 8
   ret void
 }
+
+; This 64-bit multiply should just use MUL_HI and MUL_LO, since the top
+; 32-bits of both arguments are sign bits.
+; FUNC-LABEL: @mul64_sext_c
+; EG-DAG: MULLO_INT
+; EG-DAG: MULHI_INT
+; SI-DAG: V_MUL_LO_I32
+; SI-DAG: V_MUL_HI_I32
+define void @mul64_sext_c(i64 addrspace(1)* %out, i32 %in) {
+entry:
+  %0 = sext i32 %in to i64
+  %1 = mul i64 %0, 80
+  store i64 %1, i64 addrspace(1)* %out
+  ret void
+}
+
+; A standard 64-bit multiply.  The expansion should be around 6 instructions.
+; It would be difficult to match the expansion correctly without writing
+; a really complicated list of FileCheck expressions.  I don't want
+; to confuse people who may 'break' this test with a correct optimization,
+; so this test just uses FUNC-LABEL to make sure the compiler does not
+; crash with a 'failed to select' error.
+; FUNC-LABEL: @mul64
+define void @mul64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
+entry:
+  %0 = mul i64 %a, %b
+  store i64 %0, i64 addrspace(1)* %out
+  ret void
+}

diff --git a/test/CodeGen/R600/mul_uint24-i64.ll b/test/CodeGen/R600/mul_uint24-i64.ll
deleted file mode 100644 (file)
index 95b3bcb..0000000
--- a/test/CodeGen/R600/mul_uint24-i64.ll
+++ /dev/null
@@ -1,24 +0,0 @@
-; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=EG --check-prefix=FUNC
-; RUN: llc < %s -march=r600 -mcpu=cayman | FileCheck %s --check-prefix=EG --check-prefix=FUNC
-; RUN: llc < %s -march=r600 -mcpu=SI -verify-machineinstrs | FileCheck %s --check-prefix=SI --check-prefix=FUNC
-
-; FIXME: Move this test into mul_uint24.ll once i64 mul is supported.
-; XFAIL: *
-
-; Multiply with 24-bit inputs and 64-bit output
-; FUNC_LABEL: @mul24_i64
-; EG; MUL_UINT24
-; EG: MULHI
-; SI: V_MUL_U32_U24
-; FIXME: SI support 24-bit mulhi
-; SI: V_MUL_HI_U32
-define void @mul24_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
-entry:
-  %0 = shl i64 %a, 40
-  %a_24 = lshr i64 %0, 40
-  %1 = shl i64 %b, 40
-  %b_24 = lshr i64 %1, 40
-  %2 = mul i64 %a_24, %b_24
-  store i64 %2, i64 addrspace(1)* %out
-  ret void
-}

diff --git a/test/CodeGen/R600/mul_uint24.ll b/test/CodeGen/R600/mul_uint24.ll
index 27b3717f6b75a4cac7ed19c2aad48f3efabf11fe..419f2751b83e9ca72581f49854a32b9bc72f002f 100644 (file)
--- a/test/CodeGen/R600/mul_uint24.ll
+++ b/test/CodeGen/R600/mul_uint24.ll
@@ -46,3 +46,21 @@ entry:
   store i32 %1, i32 addrspace(1)* %out
   ret void
 }
+
+; Multiply with 24-bit inputs and 64-bit output
+; FUNC_LABEL: @mul24_i64
+; EG; MUL_UINT24
+; EG: MULHI
+; SI: V_MUL_U32_U24
+; FIXME: SI support 24-bit mulhi
+; SI: V_MUL_HI_U32
+define void @mul24_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
+entry:
+  %0 = shl i64 %a, 40
+  %a_24 = lshr i64 %0, 40
+  %1 = shl i64 %b, 40
+  %b_24 = lshr i64 %1, 40
+  %2 = mul i64 %a_24, %b_24
+  store i64 %2, i64 addrspace(1)* %out
+  ret void
+}