[RISCV] Add FMV_X_W and FMV_X_H to RISCVSExtWRemoval.

Add -target-abi to sextw-removal.ll RUN lines to show benefit on
new test case.

2 files changed, 69 insertions, 15 deletions

diff --git a/llvm/lib/Target/RISCV/RISCVSExtWRemoval.cpp b/llvm/lib/Target/RISCV/RISCVSExtWRemoval.cpp
index 715d92b036e3..e4695fb2eaa7 100644
--- a/llvm/lib/Target/RISCV/RISCVSExtWRemoval.cpp
+++ b/llvm/lib/Target/RISCV/RISCVSExtWRemoval.cpp
@@ -89,6 +89,7 @@ static bool isSignExtendingOpW(const MachineInstr &MI) {
   case RISCV::FCVT_WU_S:
   case RISCV::FCVT_W_D:
   case RISCV::FCVT_WU_D:
+  case RISCV::FMV_X_W:
   // The following aren't W instructions, but are either sign extended from a
   // smaller size or put zeros in bits 63:31.
   case RISCV::LBU:
@@ -102,6 +103,7 @@ static bool isSignExtendingOpW(const MachineInstr &MI) {
   case RISCV::SEXT_B:
   case RISCV::SEXT_H:
   case RISCV::ZEXT_H_RV64:
+  case RISCV::FMV_X_H:
     return true;
   // shifting right sufficiently makes the value 32-bit sign-extended
   case RISCV::SRAI:
diff --git a/llvm/test/CodeGen/RISCV/sextw-removal.ll b/llvm/test/CodeGen/RISCV/sextw-removal.ll
index c580d26695e0..67c9aa54d9db 100644
--- a/llvm/test/CodeGen/RISCV/sextw-removal.ll
+++ b/llvm/test/CodeGen/RISCV/sextw-removal.ll
@@ -1,9 +1,9 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+f \
+; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+f -target-abi=lp64f \
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64I
-; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f \
+; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f -target-abi=lp64f \
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64ZBB
-; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f \
+; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f -target-abi=lp64f \
 ; RUN:   -riscv-disable-sextw-removal | FileCheck %s --check-prefix=NOREMOVAL
 
 define void @test1(i32 signext %arg, i32 signext %arg1) nounwind {
@@ -265,19 +265,18 @@ define void @test6(i32 signext %arg, i32 signext %arg1) nounwind {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    addi sp, sp, -16
 ; CHECK-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    fsw fs0, 4(sp) # 4-byte Folded Spill
 ; CHECK-NEXT:    sraw a0, a0, a1
-; CHECK-NEXT:    fmv.w.x ft0, zero
-; CHECK-NEXT:    fsw ft0, 4(sp) # 4-byte Folded Spill
+; CHECK-NEXT:    fmv.w.x fs0, zero
 ; CHECK-NEXT:  .LBB5_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    call baz@plt
-; CHECK-NEXT:    fmv.w.x ft0, a0
-; CHECK-NEXT:    flw ft1, 4(sp) # 4-byte Folded Reload
-; CHECK-NEXT:    feq.s a1, ft0, ft1
-; CHECK-NEXT:    fcvt.w.s a0, ft0, rtz
+; CHECK-NEXT:    feq.s a1, fa0, fs0
+; CHECK-NEXT:    fcvt.w.s a0, fa0, rtz
 ; CHECK-NEXT:    beqz a1, .LBB5_1
 ; CHECK-NEXT:  # %bb.2: # %bb7
 ; CHECK-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    flw fs0, 4(sp) # 4-byte Folded Reload
 ; CHECK-NEXT:    addi sp, sp, 16
 ; CHECK-NEXT:    ret
 ;
@@ -285,20 +284,19 @@ define void @test6(i32 signext %arg, i32 signext %arg1) nounwind {
 ; NOREMOVAL:       # %bb.0: # %bb
 ; NOREMOVAL-NEXT:    addi sp, sp, -16
 ; NOREMOVAL-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; NOREMOVAL-NEXT:    fsw fs0, 4(sp) # 4-byte Folded Spill
 ; NOREMOVAL-NEXT:    sraw a0, a0, a1
-; NOREMOVAL-NEXT:    fmv.w.x ft0, zero
-; NOREMOVAL-NEXT:    fsw ft0, 4(sp) # 4-byte Folded Spill
+; NOREMOVAL-NEXT:    fmv.w.x fs0, zero
 ; NOREMOVAL-NEXT:  .LBB5_1: # %bb2
 ; NOREMOVAL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; NOREMOVAL-NEXT:    sext.w a0, a0
 ; NOREMOVAL-NEXT:    call baz@plt
-; NOREMOVAL-NEXT:    fmv.w.x ft0, a0
-; NOREMOVAL-NEXT:    flw ft1, 4(sp) # 4-byte Folded Reload
-; NOREMOVAL-NEXT:    feq.s a1, ft0, ft1
-; NOREMOVAL-NEXT:    fcvt.w.s a0, ft0, rtz
+; NOREMOVAL-NEXT:    feq.s a1, fa0, fs0
+; NOREMOVAL-NEXT:    fcvt.w.s a0, fa0, rtz
 ; NOREMOVAL-NEXT:    beqz a1, .LBB5_1
 ; NOREMOVAL-NEXT:  # %bb.2: # %bb7
 ; NOREMOVAL-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; NOREMOVAL-NEXT:    flw fs0, 4(sp) # 4-byte Folded Reload
 ; NOREMOVAL-NEXT:    addi sp, sp, 16
 ; NOREMOVAL-NEXT:    ret
 bb:
@@ -419,3 +417,57 @@ bb2:                                              ; preds = %bb2, %bb
 bb7:                                              ; preds = %bb2
   ret void
 }
+
+define void @test10(i32 signext %arg, i32 signext %arg1) nounwind {
+; CHECK-LABEL: test10:
+; CHECK:       # %bb.0: # %bb
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    fsw fs0, 4(sp) # 4-byte Folded Spill
+; CHECK-NEXT:    sraw a0, a0, a1
+; CHECK-NEXT:    fmv.w.x fs0, zero
+; CHECK-NEXT:  .LBB8_1: # %bb2
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    call baz@plt
+; CHECK-NEXT:    feq.s a1, fa0, fs0
+; CHECK-NEXT:    fmv.x.w a0, fa0
+; CHECK-NEXT:    beqz a1, .LBB8_1
+; CHECK-NEXT:  # %bb.2: # %bb7
+; CHECK-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    flw fs0, 4(sp) # 4-byte Folded Reload
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+;
+; NOREMOVAL-LABEL: test10:
+; NOREMOVAL:       # %bb.0: # %bb
+; NOREMOVAL-NEXT:    addi sp, sp, -16
+; NOREMOVAL-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
+; NOREMOVAL-NEXT:    fsw fs0, 4(sp) # 4-byte Folded Spill
+; NOREMOVAL-NEXT:    sraw a0, a0, a1
+; NOREMOVAL-NEXT:    fmv.w.x fs0, zero
+; NOREMOVAL-NEXT:  .LBB8_1: # %bb2
+; NOREMOVAL-NEXT:    # =>This Inner Loop Header: Depth=1
+; NOREMOVAL-NEXT:    sext.w a0, a0
+; NOREMOVAL-NEXT:    call baz@plt
+; NOREMOVAL-NEXT:    feq.s a1, fa0, fs0
+; NOREMOVAL-NEXT:    fmv.x.w a0, fa0
+; NOREMOVAL-NEXT:    beqz a1, .LBB8_1
+; NOREMOVAL-NEXT:  # %bb.2: # %bb7
+; NOREMOVAL-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
+; NOREMOVAL-NEXT:    flw fs0, 4(sp) # 4-byte Folded Reload
+; NOREMOVAL-NEXT:    addi sp, sp, 16
+; NOREMOVAL-NEXT:    ret
+bb:
+  %i = ashr i32 %arg, %arg1
+  br label %bb2
+
+bb2:                                              ; preds = %bb2, %bb
+  %i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
+  %i4 = tail call float @baz(i32 signext %i3)
+  %i5 = bitcast float %i4 to i32
+  %i6 = fcmp oeq float %i4, zeroinitializer
+  br i1 %i6, label %bb7, label %bb2
+
+bb7:                                              ; preds = %bb2
+  ret void
+}