AMDGPU: Implement isExtractVecEltCheap (#122460)

Once again we have excessive TLI hooks with bad defaults. Permit this
for 32-bit element vectors, which are just use-different-register.
We should permit 16-bit vectors as cheap with legal packed instructions,
but I see some mixed improvements and regressions that need investigation.

Author: arsenm

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

@@ -1952,6 +1952,13 @@ bool SITargetLowering::isExtractSubvectorCheap(EVT ResVT, EVT SrcVT,
   return Index == 0;
 }
 
+bool SITargetLowering::isExtractVecEltCheap(EVT VT, unsigned Index) const {
+  // TODO: This should be more aggressive, particular for 16-bit element
+  // vectors. However there are some mixed improvements and regressions.
+  EVT EltTy = VT.getVectorElementType();
+  return EltTy.getSizeInBits() % 32 == 0;
+}
+
 bool SITargetLowering::isTypeDesirableForOp(unsigned Op, EVT VT) const {
   if (Subtarget->has16BitInsts() && VT == MVT::i16) {
     switch (Op) {

llvm/lib/Target/AMDGPU/SIISelLowering.h

@@ -365,6 +365,7 @@ class SITargetLowering final : public AMDGPUTargetLowering {
 
   bool isExtractSubvectorCheap(EVT ResVT, EVT SrcVT,
                                unsigned Index) const override;
+  bool isExtractVecEltCheap(EVT VT, unsigned Index) const override;
 
   bool isTypeDesirableForOp(unsigned Op, EVT VT) const override;
 

llvm/test/CodeGen/AMDGPU/mad-mix.ll

@@ -385,17 +385,15 @@ define <2 x float> @v_mad_mix_v2f32_shuffle(<2 x half> %src0, <2 x half> %src1,
 ; SDAG-CI:       ; %bb.0:
 ; SDAG-CI-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; SDAG-CI-NEXT:    v_cvt_f16_f32_e32 v3, v3
-; SDAG-CI-NEXT:    v_cvt_f16_f32_e32 v4, v5
 ; SDAG-CI-NEXT:    v_cvt_f16_f32_e32 v2, v2
-; SDAG-CI-NEXT:    v_cvt_f16_f32_e32 v5, v1
+; SDAG-CI-NEXT:    v_cvt_f16_f32_e32 v1, v1
 ; SDAG-CI-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v3, v3
-; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v1, v4
 ; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v2, v2
-; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v4, v5
-; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v5, v0
-; SDAG-CI-NEXT:    v_mad_f32 v0, v4, v2, v1
-; SDAG-CI-NEXT:    v_mac_f32_e32 v1, v5, v3
+; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v1, v1
+; SDAG-CI-NEXT:    v_cvt_f32_f16_e32 v4, v0
+; SDAG-CI-NEXT:    v_mad_f32 v0, v1, v2, v5
+; SDAG-CI-NEXT:    v_mad_f32 v1, v4, v3, v5
 ; SDAG-CI-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GISEL-CI-LABEL: v_mad_mix_v2f32_shuffle:

llvm/test/CodeGen/AMDGPU/packed-fp32.ll

@@ -549,24 +549,46 @@ bb:
   ret void
 }
 
-; GCN-LABEL: {{^}}fadd_fadd_fsub:
+; GCN-LABEL: {{^}}fadd_fadd_fsub_0:
 ; GFX900:       v_add_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, 0
 ; GFX900:       v_add_f32_e32 v{{[0-9]+}}, 0, v{{[0-9]+}}
-; PACKED-SDAG:  v_pk_add_f32 v[{{[0-9:]+}}], s[{{[0-9:]+}}], 0 op_sel_hi:[1,0]{{$}}
-; PACKED-SDAG:  v_pk_add_f32 v[{{[0-9:]+}}], v[{{[0-9:]+}}], 0 op_sel_hi:[1,0]{{$}}
+
+; PACKED-SDAG: v_add_f32_e64 v{{[0-9]+}}, s{{[0-9]+}}, 0
+; PACKED-SDAG: v_add_f32_e32 v{{[0-9]+}}, 0, v{{[0-9]+}}
+
 ; PACKED-GISEL: v_pk_add_f32 v[{{[0-9:]+}}], s[{{[0-9:]+}}], v[{{[0-9:]+}}]{{$}}
 ; PACKED-GISEL: v_pk_add_f32 v[{{[0-9:]+}}], v[{{[0-9:]+}}], s[{{[0-9:]+}}]{{$}}
-define amdgpu_kernel void @fadd_fadd_fsub(<2 x float> %arg) {
+define amdgpu_kernel void @fadd_fadd_fsub_0(<2 x float> %arg) {
 bb:
   %i12 = fadd <2 x float> zeroinitializer, %arg
-  %shift8 = shufflevector <2 x float> %i12, <2 x float> undef, <2 x i32> <i32 1, i32 undef>
+  %shift8 = shufflevector <2 x float> %i12, <2 x float> poison, <2 x i32> <i32 1, i32 poison>
   %i13 = fadd <2 x float> zeroinitializer, %shift8
   %i14 = shufflevector <2 x float> %arg, <2 x float> %i13, <2 x i32> <i32 0, i32 2>
   %i15 = fsub <2 x float> %i14, zeroinitializer
   store <2 x float> %i15, ptr undef
   ret void
 }
 
+; GCN-LABEL: {{^}}fadd_fadd_fsub:
+; GFX900:       v_add_f32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
+; GFX900:       v_add_f32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
+
+; PACKED-SDAG:  v_add_f32_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
+; PACKED-SDAG:  v_pk_add_f32 v[{{[0-9:]+}}], s[{{[0-9:]+}}], v[{{[0-9:]+}}] op_sel_hi:[1,0]{{$}}
+
+; PACKED-GISEL: v_pk_add_f32 v[{{[0-9:]+}}], s[{{[0-9:]+}}], v[{{[0-9:]+}}]{{$}}
+; PACKED-GISEL: v_pk_add_f32 v[{{[0-9:]+}}], s[{{[0-9:]+}}], v[{{[0-9:]+}}]{{$}}
+define amdgpu_kernel void @fadd_fadd_fsub(<2 x float> %arg, <2 x float> %arg1, ptr addrspace(1) %ptr) {
+bb:
+  %i12 = fadd <2 x float> %arg, %arg1
+  %shift8 = shufflevector <2 x float> %i12, <2 x float> poison, <2 x i32> <i32 1, i32 poison>
+  %i13 = fadd <2 x float> %arg1, %shift8
+  %i14 = shufflevector <2 x float> %arg, <2 x float> %i13, <2 x i32> <i32 0, i32 2>
+  %i15 = fsub <2 x float> %i14, %arg1
+  store <2 x float> %i15, ptr addrspace(1) %ptr
+  ret void
+}
+
 ; GCN-LABEL: {{^}}fadd_shuffle_v4:
 ; GFX900-COUNT-4:       v_add_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; PACKED-SDAG-COUNT-2:  v_pk_add_f32 v[{{[0-9:]+}}], v[{{[0-9:]+}}], v[{{[0-9:]+}}] op_sel_hi:[1,0]{{$}}

llvm/test/CodeGen/AMDGPU/trunc-combine.ll

@@ -184,6 +184,7 @@ define <2 x i16> @vector_trunc_high_bits_undef_lshr_rhs_alignbit_regression(i32
 ; SI:       ; %bb.0:
 ; SI-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; SI-NEXT:    v_lshr_b32_e32 v0, 16, v0
+; SI-NEXT:    v_mov_b32_e32 v1, 0
 ; SI-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; VI-LABEL: vector_trunc_high_bits_undef_lshr_rhs_alignbit_regression: