[llvm] [RISCV][VLOPT] Add support for vrgather (PR #148249)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-risc-v

Author: Mikhail R. Gadelha (mikhailramalho)

<details>
<summary>Changes</summary>

This PR adds support for the vrgather.vi, vrgather.vx, vrgather.vv, vrgatherei16.vv instructions in the RISC-V VLOptimizer.

To support vrgatherei16.vv I also needed to add support for it in getOperandLog2EEW.

This is the third PR addressing the list at #<!-- -->147647.

---
Full diff: https://github.com/llvm/llvm-project/pull/148249.diff


2 Files Affected:

- (modified) llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp (+13) 
- (modified) llvm/test/CodeGen/RISCV/rvv/vl-opt-instrs.ll (+4-8) 


``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp b/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp
index 2d9f38221d424..e940ab6c62637 100644
--- a/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp
+++ b/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp
@@ -747,6 +747,14 @@ getOperandLog2EEW(const MachineOperand &MO, const MachineRegisterInfo *MRI) {
     return TwoTimes ? MILog2SEW + 1 : MILog2SEW;
   }
 
+  // Vector Register Gather with 16-bit Index Elements Instruction
+  // Dest and source data EEW=SEW. Index vector EEW=16.
+  case RISCV::VRGATHEREI16_VV: {
+    if (MO.getOperandNo() == 2)
+      return 4;
+    return MILog2SEW;
+  }
+
   default:
     return std::nullopt;
   }
@@ -1051,6 +1059,11 @@ static bool isSupportedInstr(const MachineInstr &MI) {
   case RISCV::VSLIDEDOWN_VI:
   case RISCV::VSLIDE1UP_VX:
   case RISCV::VFSLIDE1UP_VF:
+  // Vector Register Gather Instructions
+  case RISCV::VRGATHER_VI:
+  case RISCV::VRGATHER_VV:
+  case RISCV::VRGATHER_VX:
+  case RISCV::VRGATHEREI16_VV:
   // Vector Single-Width Floating-Point Add/Subtract Instructions
   case RISCV::VFADD_VF:
   case RISCV::VFADD_VV:
diff --git a/llvm/test/CodeGen/RISCV/rvv/vl-opt-instrs.ll b/llvm/test/CodeGen/RISCV/rvv/vl-opt-instrs.ll
index 317ad0c124e73..a8eba6d3db256 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vl-opt-instrs.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vl-opt-instrs.ll
@@ -5476,9 +5476,8 @@ define <vscale x 4 x i32> @vrgather_vi(<vscale x 4 x i32> %a, <vscale x 4 x i32>
 ;
 ; VLOPT-LABEL: vrgather_vi:
 ; VLOPT:       # %bb.0:
-; VLOPT-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
-; VLOPT-NEXT:    vrgather.vi v12, v8, 5
 ; VLOPT-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; VLOPT-NEXT:    vrgather.vi v12, v8, 5
 ; VLOPT-NEXT:    vadd.vv v8, v12, v10
 ; VLOPT-NEXT:    ret
   %1 = call <vscale x 4 x i32> @llvm.riscv.vrgather.vx.nxv4i32.iXLen(<vscale x 4 x i32> poison, <vscale x 4 x i32> %a, iXLen 5, iXLen -1)
@@ -5497,9 +5496,8 @@ define <vscale x 4 x i32> @vrgather_vv(<vscale x 4 x i32> %a, <vscale x 4 x i32>
 ;
 ; VLOPT-LABEL: vrgather_vv:
 ; VLOPT:       # %bb.0:
-; VLOPT-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
-; VLOPT-NEXT:    vrgather.vv v12, v8, v10
 ; VLOPT-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; VLOPT-NEXT:    vrgather.vv v12, v8, v10
 ; VLOPT-NEXT:    vadd.vv v8, v12, v8
 ; VLOPT-NEXT:    ret
   %1 = call <vscale x 4 x i32> @llvm.riscv.vrgather.vv.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> %a, <vscale x 4 x i32> %idx, iXLen -1)
@@ -5518,9 +5516,8 @@ define <vscale x 4 x i32> @vrgather_vx(<vscale x 4 x i32> %a, iXLen %idx, <vscal
 ;
 ; VLOPT-LABEL: vrgather_vx:
 ; VLOPT:       # %bb.0:
-; VLOPT-NEXT:    vsetvli a2, zero, e32, m2, ta, ma
-; VLOPT-NEXT:    vrgather.vx v12, v8, a0
 ; VLOPT-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
+; VLOPT-NEXT:    vrgather.vx v12, v8, a0
 ; VLOPT-NEXT:    vadd.vv v8, v12, v10
 ; VLOPT-NEXT:    ret
   %1 = call <vscale x 4 x i32> @llvm.riscv.vrgather.vx.nxv4i32.iXLen(<vscale x 4 x i32> poison, <vscale x 4 x i32> %a, iXLen %idx, iXLen -1)
@@ -5539,9 +5536,8 @@ define <vscale x 4 x i32> @vrgatherei16_vv(<vscale x 4 x i32> %a, <vscale x 4 x
 ;
 ; VLOPT-LABEL: vrgatherei16_vv:
 ; VLOPT:       # %bb.0:
-; VLOPT-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
-; VLOPT-NEXT:    vrgatherei16.vv v12, v8, v10
 ; VLOPT-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; VLOPT-NEXT:    vrgatherei16.vv v12, v8, v10
 ; VLOPT-NEXT:    vadd.vv v8, v12, v8
 ; VLOPT-NEXT:    ret
   %1 = call <vscale x 4 x i32> @llvm.riscv.vrgatherei16.vv.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> %a, <vscale x 4 x i16> %idx, iXLen -1)

``````````

</details>


https://github.com/llvm/llvm-project/pull/148249