[PATCH] D139874: [AMDGPU] Lower VGPR to physical SGPR COPY to S_MOV_B32 if VGPR contains the compile time constant

Alexander via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Dec 13 09:20:46 PST 2022


alex-t updated this revision to Diff 482520.
alex-t added a comment.

add operand instead of adding immediate


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D139874/new/

https://reviews.llvm.org/D139874

Files:
  llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
  llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll


Index: llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/vgpr_constant_to_sgpr.ll
@@ -0,0 +1,61 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -O0 -mcpu=gfx1030 < %s | FileCheck %s
+
+target triple = "amdgcn-amd-amdhsa"
+
+; Unknown functions are conservatively passed all implicit parameters
+declare void @unknown_call()
+; Use the same constant as a sgpr parameter (for the kernel id) and for a vector operation
+define protected amdgpu_kernel void @kern(ptr %addr) !llvm.amdgcn.lds.kernel.id !0 {
+; CHECK-LABEL: kern:
+; CHECK:       ; %bb.0:
+; CHECK-NEXT:    s_mov_b32 s32, 0
+; CHECK-NEXT:    s_add_u32 s12, s12, s17
+; CHECK-NEXT:    s_addc_u32 s13, s13, 0
+; CHECK-NEXT:    s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s12
+; CHECK-NEXT:    s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s13
+; CHECK-NEXT:    s_add_u32 s0, s0, s17
+; CHECK-NEXT:    s_addc_u32 s1, s1, 0
+; CHECK-NEXT:    v_writelane_b32 v40, s16, 0
+; CHECK-NEXT:    s_mov_b32 s13, s15
+; CHECK-NEXT:    s_mov_b32 s12, s14
+; CHECK-NEXT:    v_readlane_b32 s14, v40, 0
+; CHECK-NEXT:    s_mov_b64 s[16:17], s[8:9]
+; CHECK-NEXT:    s_load_dwordx2 s[8:9], s[16:17], 0x0
+; CHECK-NEXT:    v_mov_b32_e32 v5, 42
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
+; CHECK-NEXT:    v_mov_b32_e32 v3, s8
+; CHECK-NEXT:    v_mov_b32_e32 v4, s9
+; CHECK-NEXT:    flat_store_dword v[3:4], v5
+; CHECK-NEXT:    s_mov_b64 s[18:19], 8
+; CHECK-NEXT:    s_mov_b32 s8, s16
+; CHECK-NEXT:    s_mov_b32 s9, s17
+; CHECK-NEXT:    s_mov_b32 s16, s18
+; CHECK-NEXT:    s_mov_b32 s15, s19
+; CHECK-NEXT:    s_add_u32 s8, s8, s16
+; CHECK-NEXT:    s_addc_u32 s15, s9, s15
+; CHECK-NEXT:    ; kill: def $sgpr8 killed $sgpr8 def $sgpr8_sgpr9
+; CHECK-NEXT:    s_mov_b32 s9, s15
+; CHECK-NEXT:    s_getpc_b64 s[16:17]
+; CHECK-NEXT:    s_add_u32 s16, s16, unknown_call at gotpcrel32@lo+4
+; CHECK-NEXT:    s_addc_u32 s17, s17, unknown_call at gotpcrel32@hi+12
+; CHECK-NEXT:    s_load_dwordx2 s[16:17], s[16:17], 0x0
+; CHECK-NEXT:    s_mov_b64 s[22:23], s[2:3]
+; CHECK-NEXT:    s_mov_b64 s[20:21], s[0:1]
+; CHECK-NEXT:    s_mov_b32 s15, 20
+; CHECK-NEXT:    v_lshlrev_b32_e64 v2, s15, v2
+; CHECK-NEXT:    s_mov_b32 s15, 10
+; CHECK-NEXT:    v_lshlrev_b32_e64 v1, s15, v1
+; CHECK-NEXT:    v_or3_b32 v31, v0, v1, v2
+; CHECK-NEXT:    s_mov_b32 s15, 42
+; CHECK-NEXT:    s_mov_b64 s[0:1], s[20:21]
+; CHECK-NEXT:    s_mov_b64 s[2:3], s[22:23]
+; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
+; CHECK-NEXT:    s_swappc_b64 s[30:31], s[16:17]
+; CHECK-NEXT:    s_endpgm
+  store i32 42, ptr %addr
+  call fastcc void @unknown_call()
+  ret void
+}
+
+!0 = !{i32 42}
Index: llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
+++ llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
@@ -845,6 +845,20 @@
               TII->get(AMDGPU::V_READFIRSTLANE_B32), TmpReg)
           .add(MI.getOperand(1));
       MI.getOperand(1).setReg(TmpReg);
+    } else {
+      MachineInstr *DefMI = MRI->getVRegDef(SrcReg);
+      if (DefMI && DefMI->isMoveImmediate()) {
+        MachineOperand SrcConst = DefMI->getOperand(AMDGPU::getNamedOperandIdx(
+            DefMI->getOpcode(), AMDGPU::OpName::src0));
+        if (SrcConst.isImm()) {
+            Register TmpReg =
+                MRI->createVirtualRegister(&AMDGPU::SReg_32_XM0RegClass);
+            BuildMI(*MI.getParent(), MI, MI.getDebugLoc(),
+                    TII->get(AMDGPU::S_MOV_B32), TmpReg)
+                .add(SrcConst);
+            MI.getOperand(1).setReg(TmpReg);
+        }
+      }
     }
     return true;
   }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D139874.482520.patch
Type: text/x-patch
Size: 3748 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221213/72357836/attachment.bin>


More information about the llvm-commits mailing list