[RISCV] Optimize scalable frame setup when VLEN is precisely known

If we know the exact value of VLEN, the frame offset adjustment for scalable stack slots becomes a fixed constant. This avoids the need to read vlenb, and may allow the offset to be folded into the immediate field of an add/sub.

We could go further here, and fold the offset into a single larger frame adjustment - instead of having a separate scalable adjustment step - but that requires a bit more code reorganization. I may (or may not) return to that in a future patch.

Differential Revision: https://reviews.llvm.org/D137593

diff --git a/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp b/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
index b7aefe1..4f79339 100644 (file)
--- a/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVFrameLowering.cpp
@@ -373,7 +373,24 @@ void RISCVFrameLowering::adjustStackForRVV(MachineFunction &MF,
   assert(Amount != 0 && "Did not need to adjust stack pointer for RVV.");
 
   const RISCVInstrInfo *TII = STI.getInstrInfo();
-  Register SPReg = getSPReg(STI);
+  const Register SPReg = getSPReg(STI);
+
+  // Optimize compile time offset case
+  if (STI.getRealMinVLen() == STI.getRealMaxVLen()) {
+    // 1. Multiply the number of v-slots by the (constant) length of register
+    const int64_t VLENB = STI.getRealMinVLen() / 8;
+    assert(Amount % 8 == 0 &&
+           "Reserve the stack by the multiple of one vector size.");
+    const int64_t NumOfVReg = Amount / 8;
+    const int64_t Offset = NumOfVReg * VLENB;
+    if (!isInt<32>(Offset)) {
+      report_fatal_error(
+        "Frame size outside of the signed 32-bit range not supported");
+    }
+    adjustReg(MBB, MBBI, DL, SPReg, SPReg, Offset, Flag);
+    return;
+  }
+
   unsigned Opc = RISCV::ADD;
   if (Amount < 0) {
     Amount = -Amount;

diff --git a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
index d640e22..23e8277 100644 (file)
--- a/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/rv64-spill-vector-csr.ll
@@ -87,9 +87,7 @@ define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double
 ; SPILL-O2-VLEN128-NEXT:    addi sp, sp, -32
 ; SPILL-O2-VLEN128-NEXT:    sd ra, 24(sp) # 8-byte Folded Spill
 ; SPILL-O2-VLEN128-NEXT:    sd s0, 16(sp) # 8-byte Folded Spill
-; SPILL-O2-VLEN128-NEXT:    csrr a1, vlenb
-; SPILL-O2-VLEN128-NEXT:    slli a1, a1, 1
-; SPILL-O2-VLEN128-NEXT:    sub sp, sp, a1
+; SPILL-O2-VLEN128-NEXT:    addi sp, sp, -32
 ; SPILL-O2-VLEN128-NEXT:    mv s0, a0
 ; SPILL-O2-VLEN128-NEXT:    addi a1, sp, 16
 ; SPILL-O2-VLEN128-NEXT:    vs1r.v v8, (a1) # Unknown-size Folded Spill
@@ -106,9 +104,7 @@ define <vscale x 1 x double> @foo(<vscale x 1 x double> %a, <vscale x 1 x double
 ; SPILL-O2-VLEN128-NEXT:    addi a0, sp, 16
 ; SPILL-O2-VLEN128-NEXT:    vl1r.v v9, (a0) # Unknown-size Folded Reload
 ; SPILL-O2-VLEN128-NEXT:    vfadd.vv v8, v9, v8
-; SPILL-O2-VLEN128-NEXT:    csrr a0, vlenb
-; SPILL-O2-VLEN128-NEXT:    slli a0, a0, 1
-; SPILL-O2-VLEN128-NEXT:    add sp, sp, a0
+; SPILL-O2-VLEN128-NEXT:    addi sp, sp, 32
 ; SPILL-O2-VLEN128-NEXT:    ld ra, 24(sp) # 8-byte Folded Reload
 ; SPILL-O2-VLEN128-NEXT:    ld s0, 16(sp) # 8-byte Folded Reload
 ; SPILL-O2-VLEN128-NEXT:    addi sp, sp, 32