diff --git a/src/amd/llvm/ac_llvm_build.c b/src/amd/llvm/ac_llvm_build.c
index 4c09ed8feea..a5b145397b1 100644
--- a/src/amd/llvm/ac_llvm_build.c
+++ b/src/amd/llvm/ac_llvm_build.c
@@ -1090,15 +1090,6 @@ LLVMValueRef ac_build_gep_ptr(struct ac_llvm_context *ctx, LLVMTypeRef type, LLV
    return LLVMBuildGEP2(ctx->builder, type, base_ptr, &index, 1, "");
 }
 
-LLVMValueRef ac_build_gep0(struct ac_llvm_context *ctx, LLVMValueRef base_ptr, LLVMValueRef index)
-{
-   LLVMValueRef indices[2] = {
-      ctx->i32_0,
-      index,
-   };
-   return LLVMBuildGEP(ctx->builder, base_ptr, indices, 2, "");
-}
-
 LLVMTypeRef ac_build_gep0_type(LLVMTypeRef pointee_type, LLVMValueRef index)
 {
    switch (LLVMGetTypeKind(pointee_type)) {
@@ -1121,7 +1112,7 @@ LLVMTypeRef ac_build_gep0_type(LLVMTypeRef pointee_type, LLVMValueRef index)
    return NULL;
 }
 
-LLVMValueRef ac_build_gep0_2(struct ac_llvm_context *ctx, LLVMTypeRef pointee_type, LLVMValueRef value, LLVMValueRef index)
+LLVMValueRef ac_build_gep0(struct ac_llvm_context *ctx, LLVMTypeRef pointee_type, LLVMValueRef value, LLVMValueRef index)
 {
    LLVMValueRef indices[2] = {
       ctx->i32_0,
@@ -1136,16 +1127,10 @@ LLVMValueRef ac_build_pointer_add(struct ac_llvm_context *ctx, LLVMTypeRef type,
    return LLVMBuildGEP2(ctx->builder, type, ptr, &index, 1, "");
 }
 
-void ac_build_indexed_store(struct ac_llvm_context *ctx, LLVMValueRef base_ptr, LLVMValueRef index,
+void ac_build_indexed_store(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr, LLVMValueRef index,
                             LLVMValueRef value)
 {
-   LLVMBuildStore(ctx->builder, value, ac_build_gep0(ctx, base_ptr, index));
-}
-
-void ac_build_indexed_store2(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr, LLVMValueRef index,
-                             LLVMValueRef value)
-{
-   LLVMBuildStore(ctx->builder, value, ac_build_gep0_2(ctx, type, base_ptr, index));
+   LLVMBuildStore(ctx->builder, value, ac_build_gep0(ctx, type, base_ptr, index));
 }
 
 /**
@@ -1176,30 +1161,9 @@ void ac_build_indexed_store2(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVM
  *      ptr2 = LLVMBuildInBoundsGEP(ptr1, 32 / elemsize);
  *      sampler = load(ptr2); // becomes "s_load ptr1, 32" thanks to InBounds
  */
-static LLVMValueRef ac_build_load_custom(struct ac_llvm_context *ctx, LLVMValueRef base_ptr,
-                                         LLVMValueRef index, bool uniform, bool invariant,
-                                         bool no_unsigned_wraparound)
-{
-   LLVMValueRef pointer, result;
-
-   if (no_unsigned_wraparound &&
-       LLVMGetPointerAddressSpace(LLVMTypeOf(base_ptr)) == AC_ADDR_SPACE_CONST_32BIT)
-      pointer = LLVMBuildInBoundsGEP(ctx->builder, base_ptr, &index, 1, "");
-   else
-      pointer = LLVMBuildGEP(ctx->builder, base_ptr, &index, 1, "");
-
-   if (uniform)
-      LLVMSetMetadata(pointer, ctx->uniform_md_kind, ctx->empty_md);
-   result = LLVMBuildLoad(ctx->builder, pointer, "");
-   if (invariant)
-      LLVMSetMetadata(result, ctx->invariant_load_md_kind, ctx->empty_md);
-   LLVMSetAlignment(result, 4);
-   return result;
-}
-
-static LLVMValueRef ac_build_load_custom2(struct ac_llvm_context *ctx, LLVMTypeRef type,
-                                          LLVMValueRef base_ptr, LLVMValueRef index,
-                                          bool uniform, bool invariant, bool no_unsigned_wraparound)
+static LLVMValueRef ac_build_load_custom(struct ac_llvm_context *ctx, LLVMTypeRef type,
+                                         LLVMValueRef base_ptr, LLVMValueRef index,
+                                         bool uniform, bool invariant, bool no_unsigned_wraparound)
 {
    LLVMValueRef pointer, result;
 
@@ -1220,39 +1184,28 @@ static LLVMValueRef ac_build_load_custom2(struct ac_llvm_context *ctx, LLVMTypeR
 
 LLVMValueRef ac_build_load(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr, LLVMValueRef index)
 {
-   return ac_build_load_custom2(ctx, type, base_ptr, index, false, false, false);
+   return ac_build_load_custom(ctx, type, base_ptr, index, false, false, false);
 }
 
 LLVMValueRef ac_build_load_invariant(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
                                      LLVMValueRef index)
 {
-   return ac_build_load_custom2(ctx, type, base_ptr, index, false, true, false);
+   return ac_build_load_custom(ctx, type, base_ptr, index, false, true, false);
 }
 
 /* This assumes that there is no unsigned integer wraparound during the address
  * computation, excluding all GEPs within base_ptr. */
-LLVMValueRef ac_build_load_to_sgpr(struct ac_llvm_context *ctx, LLVMValueRef base_ptr,
+LLVMValueRef ac_build_load_to_sgpr(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
                                    LLVMValueRef index)
 {
-   return ac_build_load_custom(ctx, base_ptr, index, true, true, true);
-}
-
-LLVMValueRef ac_build_load_to_sgpr2(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
-                                    LLVMValueRef index)
-{
-   return ac_build_load_custom2(ctx, type, base_ptr, index, true, true, true);
+   return ac_build_load_custom(ctx, type, base_ptr, index, true, true, true);
 }
 
 /* See ac_build_load_custom() documentation. */
-LLVMValueRef ac_build_load_to_sgpr_uint_wraparound(struct ac_llvm_context *ctx,
+LLVMValueRef ac_build_load_to_sgpr_uint_wraparound(struct ac_llvm_context *ctx, LLVMTypeRef type,
                                                    LLVMValueRef base_ptr, LLVMValueRef index)
 {
-   return ac_build_load_custom(ctx, base_ptr, index, true, true, false);
-}
-LLVMValueRef ac_build_load_to_sgpr_uint_wraparound2(struct ac_llvm_context *ctx, LLVMTypeRef type,
-                                                   LLVMValueRef base_ptr, LLVMValueRef index)
-{
-   return ac_build_load_custom2(ctx, type, base_ptr, index, true, true, false);
+   return ac_build_load_custom(ctx, type, base_ptr, index, true, true, false);
 }
 
 static unsigned get_load_cache_policy(struct ac_llvm_context *ctx, unsigned cache_policy)
@@ -2830,14 +2783,14 @@ void ac_declare_lds_as_pointer(struct ac_llvm_context *ctx)
 
 LLVMValueRef ac_lds_load(struct ac_llvm_context *ctx, LLVMValueRef dw_addr)
 {
-   LLVMValueRef v = ac_build_gep0_2(ctx, ctx->lds.t, ctx->lds.v, dw_addr);
+   LLVMValueRef v = ac_build_gep0(ctx, ctx->lds.t, ctx->lds.v, dw_addr);
    return LLVMBuildLoad2(ctx->builder, ctx->i32, v, "");
 }
 
 void ac_lds_store(struct ac_llvm_context *ctx, LLVMValueRef dw_addr, LLVMValueRef value)
 {
    value = ac_to_integer(ctx, value);
-   ac_build_indexed_store2(ctx, ctx->lds.t, ctx->lds.v, dw_addr, value);
+   ac_build_indexed_store(ctx, ctx->lds.t, ctx->lds.v, dw_addr, value);
 }
 
 LLVMValueRef ac_find_lsb(struct ac_llvm_context *ctx, LLVMTypeRef dst_type, LLVMValueRef src0)
diff --git a/src/amd/llvm/ac_llvm_build.h b/src/amd/llvm/ac_llvm_build.h
index aeee00ee517..776faedaa92 100644
--- a/src/amd/llvm/ac_llvm_build.h
+++ b/src/amd/llvm/ac_llvm_build.h
@@ -254,28 +254,22 @@ LLVMValueRef ac_build_fs_interp_mov(struct ac_llvm_context *ctx, LLVMValueRef pa
 LLVMValueRef ac_build_gep_ptr(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
                               LLVMValueRef index);
 
-LLVMValueRef ac_build_gep0(struct ac_llvm_context *ctx, LLVMValueRef value, LLVMValueRef index);
 LLVMValueRef ac_build_pointer_add(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef ptr,
                                   LLVMValueRef index);
 
 LLVMTypeRef ac_build_gep0_type(LLVMTypeRef pointee_type, LLVMValueRef index);
-LLVMValueRef ac_build_gep0_2(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef value, LLVMValueRef index);
+LLVMValueRef ac_build_gep0(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef value, LLVMValueRef index);
 
-void ac_build_indexed_store(struct ac_llvm_context *ctx, LLVMValueRef base_ptr, LLVMValueRef index,
+void ac_build_indexed_store(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr, LLVMValueRef index,
                             LLVMValueRef value);
-void ac_build_indexed_store2(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr, LLVMValueRef index,
-                             LLVMValueRef value);
 
 LLVMValueRef ac_build_load(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr, LLVMValueRef index);
 LLVMValueRef ac_build_load_invariant(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
                                      LLVMValueRef index);
-LLVMValueRef ac_build_load_to_sgpr(struct ac_llvm_context *ctx, LLVMValueRef base_ptr,
+LLVMValueRef ac_build_load_to_sgpr(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
                                    LLVMValueRef index);
-LLVMValueRef ac_build_load_to_sgpr2(struct ac_llvm_context *ctx, LLVMTypeRef type, LLVMValueRef base_ptr,
-                                    LLVMValueRef index);
-LLVMValueRef ac_build_load_to_sgpr_uint_wraparound(struct ac_llvm_context *ctx,
-                                                   LLVMValueRef base_ptr, LLVMValueRef index);
-LLVMValueRef ac_build_load_to_sgpr_uint_wraparound2(struct ac_llvm_context *ctx, LLVMTypeRef type,
+
+LLVMValueRef ac_build_load_to_sgpr_uint_wraparound(struct ac_llvm_context *ctx, LLVMTypeRef type,
                                                    LLVMValueRef base_ptr, LLVMValueRef index);
 
 void ac_build_buffer_store_dword(struct ac_llvm_context *ctx, LLVMValueRef rsrc, LLVMValueRef vdata,
diff --git a/src/amd/llvm/ac_nir_to_llvm.c b/src/amd/llvm/ac_nir_to_llvm.c
index 5bf2bc3415f..19d6a34537a 100644
--- a/src/amd/llvm/ac_nir_to_llvm.c
+++ b/src/amd/llvm/ac_nir_to_llvm.c
@@ -4115,7 +4115,7 @@ static bool visit_intrinsic(struct ac_nir_context *ctx, nir_intrinsic_instr *ins
       break;
    case nir_intrinsic_load_scratch: {
       LLVMValueRef offset = get_src(ctx, instr->src[0]);
-      LLVMValueRef ptr = ac_build_gep0_2(&ctx->ac, ctx->scratch.t, ctx->scratch.v, offset);
+      LLVMValueRef ptr = ac_build_gep0(&ctx->ac, ctx->scratch.t, ctx->scratch.v, offset);
       LLVMTypeRef comp_type = LLVMIntTypeInContext(ctx->ac.context, instr->dest.ssa.bit_size);
       LLVMTypeRef vec_type = instr->dest.ssa.num_components == 1
                                 ? comp_type
@@ -4125,7 +4125,7 @@ static bool visit_intrinsic(struct ac_nir_context *ctx, nir_intrinsic_instr *ins
    }
    case nir_intrinsic_store_scratch: {
       LLVMValueRef offset = get_src(ctx, instr->src[1]);
-      LLVMValueRef ptr = ac_build_gep0_2(&ctx->ac, ctx->scratch.t, ctx->scratch.v, offset);
+      LLVMValueRef ptr = ac_build_gep0(&ctx->ac, ctx->scratch.t, ctx->scratch.v, offset);
       LLVMTypeRef comp_type = LLVMIntTypeInContext(ctx->ac.context, instr->src[0].ssa->bit_size);
       LLVMValueRef src = get_src(ctx, instr->src[0]);
       unsigned wrmask = nir_intrinsic_write_mask(instr);
@@ -4154,7 +4154,7 @@ static bool visit_intrinsic(struct ac_nir_context *ctx, nir_intrinsic_instr *ins
       LLVMValueRef cond = LLVMBuildICmp(ctx->ac.builder, LLVMIntULT, offset, size, "");
       offset = LLVMBuildSelect(ctx->ac.builder, cond, offset, size, "");
 
-      LLVMValueRef ptr = ac_build_gep0_2(&ctx->ac, ctx->constant_data.t, ctx->constant_data.v, offset);
+      LLVMValueRef ptr = ac_build_gep0(&ctx->ac, ctx->constant_data.t, ctx->constant_data.v, offset);
       LLVMTypeRef comp_type = LLVMIntTypeInContext(ctx->ac.context, instr->dest.ssa.bit_size);
       LLVMTypeRef vec_type = instr->dest.ssa.num_components == 1
                                 ? comp_type
diff --git a/src/amd/vulkan/radv_nir_to_llvm.c b/src/amd/vulkan/radv_nir_to_llvm.c
index 64acae0508b..46c1f8646cd 100644
--- a/src/amd/vulkan/radv_nir_to_llvm.c
+++ b/src/amd/vulkan/radv_nir_to_llvm.c
@@ -114,7 +114,7 @@ load_descriptor_sets(struct radv_shader_context *ctx)
          int i = u_bit_scan(&mask);
 
          ctx->descriptor_sets[i] =
-            ac_build_load_to_sgpr2(&ctx->ac, type, desc_sets, LLVMConstInt(ctx->ac.i32, i, false));
+            ac_build_load_to_sgpr(&ctx->ac, type, desc_sets, LLVMConstInt(ctx->ac.i32, i, false));
          LLVMSetAlignment(ctx->descriptor_sets[i], 4);
       }
    } else {
@@ -400,7 +400,7 @@ load_vs_input(struct radv_shader_context *ctx, unsigned driver_location, LLVMTyp
    desc_index = util_bitcount(ctx->shader_info->vs.vb_desc_usage_mask &
                               u_bit_consecutive(0, desc_index));
    t_offset = LLVMConstInt(ctx->ac.i32, desc_index, false);
-   t_list = ac_build_load_to_sgpr2(&ctx->ac, t_list_type, t_list_ptr, t_offset);
+   t_list = ac_build_load_to_sgpr(&ctx->ac, t_list_type, t_list_ptr, t_offset);
 
    /* Always split typed vertex buffer loads on GFX6 and GFX10+ to avoid any alignment issues that
     * triggers memory violations and eventually a GPU hang. This can happen if the stride (static or
@@ -807,7 +807,7 @@ radv_emit_streamout(struct radv_shader_context *ctx, unsigned stream)
 
          LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, i, false);
 
-         so_buffers[i] = ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr, offset);
+         so_buffers[i] = ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr, offset);
 
          LLVMValueRef so_offset = ac_get_arg(&ctx->ac, ctx->args->ac.streamout_offset[i]);
 
@@ -1181,11 +1181,11 @@ ac_setup_rings(struct radv_shader_context *ctx)
       unsigned ring = ctx->stage == MESA_SHADER_GEOMETRY ? RING_ESGS_GS : RING_ESGS_VS;
       LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, ring, false);
 
-      ctx->esgs_ring = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i8, ctx->ring_offsets, offset);
+      ctx->esgs_ring = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.i8, ctx->ring_offsets, offset);
    }
 
    if (ctx->args->is_gs_copy_shader) {
-      ctx->gsvs_ring[0] = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i8, ctx->ring_offsets,
+      ctx->gsvs_ring[0] = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.i8, ctx->ring_offsets,
                                                 LLVMConstInt(ctx->ac.i32, RING_GSVS_VS, false));
    }
 
@@ -1203,7 +1203,7 @@ ac_setup_rings(struct radv_shader_context *ctx)
       unsigned num_records = ctx->ac.wave_size;
       LLVMValueRef base_ring;
 
-      base_ring = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i8, ctx->ring_offsets,
+      base_ring = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.i8, ctx->ring_offsets,
                                         LLVMConstInt(ctx->ac.i32, RING_GSVS_GS, false));
 
       for (unsigned stream = 0; stream < 4; stream++) {
@@ -1243,9 +1243,9 @@ ac_setup_rings(struct radv_shader_context *ctx)
    }
 
    if (ctx->stage == MESA_SHADER_TESS_CTRL || ctx->stage == MESA_SHADER_TESS_EVAL) {
-      ctx->hs_ring_tess_offchip = ac_build_load_to_sgpr2(
+      ctx->hs_ring_tess_offchip = ac_build_load_to_sgpr(
          &ctx->ac, ctx->ac.i8, ctx->ring_offsets, LLVMConstInt(ctx->ac.i32, RING_HS_TESS_OFFCHIP, false));
-      ctx->hs_ring_tess_factor = ac_build_load_to_sgpr2(
+      ctx->hs_ring_tess_factor = ac_build_load_to_sgpr(
          &ctx->ac, ctx->ac.i8, ctx->ring_offsets, LLVMConstInt(ctx->ac.i32, RING_HS_TESS_FACTOR, false));
    }
 }
diff --git a/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c b/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
index aae8a23379f..27b907cdd55 100644
--- a/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
+++ b/src/gallium/drivers/radeonsi/gfx10_shader_ngg.c
@@ -67,8 +67,8 @@ static LLVMValueRef ngg_get_query_buf(struct si_shader_context *ctx)
 {
    LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
-   return ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr,
-                                 LLVMConstInt(ctx->ac.i32, SI_GS_QUERY_BUF, false));
+   return ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr,
+                                LLVMConstInt(ctx->ac.i32, SI_GS_QUERY_BUF, false));
 }
 
 static LLVMValueRef ngg_get_emulated_counters_buf(struct si_shader_context *ctx)
@@ -76,8 +76,8 @@ static LLVMValueRef ngg_get_emulated_counters_buf(struct si_shader_context *ctx)
    LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
 
-   return ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr,
-                                 LLVMConstInt(ctx->ac.i32, SI_GS_QUERY_EMULATED_COUNTERS_BUF, false));
+   return ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr,
+                                LLVMConstInt(ctx->ac.i32, SI_GS_QUERY_EMULATED_COUNTERS_BUF, false));
 }
 
 /**
@@ -253,7 +253,7 @@ static void build_streamout_vertex(struct si_shader_context *ctx, LLVMValueRef *
 
       for (unsigned comp = 0; comp < 4; comp++) {
          LLVMValueRef idx = LLVMConstInt(ctx->ac.i32, 4 * reg + comp, false);
-         LLVMValueRef v = ac_build_gep0_2(&ctx->ac, vertexptr.t, vertexptr.v, idx);
+         LLVMValueRef v = ac_build_gep0(&ctx->ac, vertexptr.t, vertexptr.v, idx);
          out.values[comp] = LLVMBuildLoad2(builder, ac_build_gep0_type(vertexptr.t, idx), v, "");
          out.vertex_streams = info->output_streams[reg];
       }
@@ -327,7 +327,7 @@ static void build_streamout(struct si_shader_context *ctx, struct ngg_streamout
          ac_build_writelane(&ctx->ac, prim_stride_dw_vgpr, prim_stride_dw[buffer],
                             LLVMConstInt(ctx->ac.i32, buffer, false));
 
-      so_buffer[buffer] = ac_build_load_to_sgpr2(
+      so_buffer[buffer] = ac_build_load_to_sgpr(
          &ctx->ac, type, buf_ptr, LLVMConstInt(ctx->ac.i32, SI_VS_STREAMOUT_BUF0 + buffer, false));
    }
 
@@ -345,7 +345,7 @@ static void build_streamout(struct si_shader_context *ctx, struct ngg_streamout
       ac_build_ifcc(&ctx->ac, tmp, 5210);
       {
          if (isgs) {
-            LLVMValueRef vt = ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, tid);
+            LLVMValueRef vt = ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, tid);
             tmp = LLVMBuildLoad2(builder, ac_build_gep0_type(ctx->gs_ngg_scratch.t, tid), vt, "");
          } else {
             tmp = ac_build_writelane(&ctx->ac, ctx->ac.i32_0, ngg_get_prim_cnt(ctx), ctx->ac.i32_0);
@@ -452,7 +452,7 @@ static void build_streamout(struct si_shader_context *ctx, struct ngg_streamout
          LLVMBuildStore(builder, tmp, offsets_vgpr);
 
          tmp2 = LLVMBuildAdd(builder, ac_get_thread_id(&ctx->ac), scratch_offset_basev, "");
-         tmp2 = ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, tmp2);
+         tmp2 = ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, tmp2);
          LLVMBuildStore(builder, tmp, tmp2);
       }
       ac_build_endif(&ctx->ac, 5210);
@@ -546,7 +546,7 @@ static void build_streamout(struct si_shader_context *ctx, struct ngg_streamout
       ac_build_ifcc(&ctx->ac, tmp, 5225);
       {
          tmp = LLVMBuildAdd(builder, ac_get_thread_id(&ctx->ac), scratch_emit_basev, "");
-         tmp = ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, tmp);
+         tmp = ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, tmp);
          LLVMBuildStore(builder, emit_vgpr, tmp);
       }
       ac_build_endif(&ctx->ac, 5225);
@@ -566,7 +566,7 @@ static void build_streamout(struct si_shader_context *ctx, struct ngg_streamout
          primemit_scan[stream].enable_exclusive = true;
          primemit_scan[stream].op = nir_op_iadd;
          primemit_scan[stream].src = nggso->prim_enable[stream];
-         primemit_scan[stream].scratch = ac_build_gep0_2(
+         primemit_scan[stream].scratch = ac_build_gep0(
             &ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v,
             LLVMConstInt(ctx->ac.i32, 12 + 8 * stream, false));
          primemit_scan[stream].waveidx = get_wave_id_in_tg(ctx);
@@ -592,7 +592,7 @@ static void build_streamout(struct si_shader_context *ctx, struct ngg_streamout
       LLVMValueRef scratch_vgpr;
 
       LLVMValueRef idx = ac_get_thread_id(&ctx->ac);
-      LLVMValueRef v = ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, idx);
+      LLVMValueRef v = ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, idx);
       scratch_vgpr = LLVMBuildLoad2(builder, ac_build_gep0_type(ctx->gs_ngg_scratch.t, idx), v, "");
 
       for (unsigned buffer = 0; buffer < 4; ++buffer) {
@@ -779,7 +779,7 @@ static void load_vertex_counts(struct si_shader_context *ctx, struct ac_llvm_poi
     */
    ac_build_ifcc(&ctx->ac, LLVMBuildICmp(builder, LLVMIntULT, tid,
                                          LLVMConstInt(ctx->ac.i32, num_i8vec4, 0), ""), 17771);
-   LLVMValueRef v = ac_build_gep0_2(&ctx->ac, lds.t, lds.v, tid);
+   LLVMValueRef v = ac_build_gep0(&ctx->ac, lds.t, lds.v, tid);
    LLVMBuildStore(builder, LLVMBuildLoad2(builder, ac_build_gep0_type(lds.t, tid), v, ""), i8vec4_lane);
    ac_build_endif(&ctx->ac, 17771);
 
@@ -956,8 +956,8 @@ static void cull_primitive(struct si_shader_context *ctx,
    LLVMValueRef ptr = ac_get_arg(&ctx->ac, ctx->small_prim_cull_info);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->small_prim_cull_info);
    /* Lines will always use the non-AA viewport transformation. */
-   LLVMValueRef vp = ac_build_load_to_sgpr2(&ctx->ac, type, ptr,
-                                            prim_is_lines ? ctx->ac.i32_1 : ctx->ac.i32_0);
+   LLVMValueRef vp = ac_build_load_to_sgpr(&ctx->ac, type, ptr,
+                                           prim_is_lines ? ctx->ac.i32_1 : ctx->ac.i32_0);
    vp = LLVMBuildBitCast(builder, vp, ctx->ac.v4f32, "");
    vp_scale[0] = ac_llvm_extract_elem(&ctx->ac, vp, 0);
    vp_scale[1] = ac_llvm_extract_elem(&ctx->ac, vp, 1);
@@ -970,7 +970,7 @@ static void cull_primitive(struct si_shader_context *ctx,
    options.cull_w = true;
 
    if (prim_is_lines) {
-      LLVMValueRef terms = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.v2f32, ptr, LLVMConstInt(ctx->ac.i32, 4, 0));
+      LLVMValueRef terms = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.v2f32, ptr, LLVMConstInt(ctx->ac.i32, 4, 0));
       terms = LLVMBuildBitCast(builder, terms, ctx->ac.v2f32, "");
       clip_half_line_width[0] = ac_llvm_extract_elem(&ctx->ac, terms, 0);
       clip_half_line_width[1] = ac_llvm_extract_elem(&ctx->ac, terms, 1);
@@ -1062,14 +1062,14 @@ void gfx10_ngg_culling_build_end(struct si_shader_context *ctx)
          /* Store Position.W into LDS. */
          LLVMBuildStore(
             builder, ac_to_integer(&ctx->ac, position[3]),
-            ac_build_gep0_2(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_pos_cull_w, 0)));
+            ac_build_gep0(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_pos_cull_w, 0)));
 
          /* Store Position.XY / W into LDS. */
          for (unsigned chan = 0; chan < 2; chan++) {
             LLVMValueRef val = ac_build_fdiv(&ctx->ac, position[chan], position[3]);
             LLVMBuildStore(
                builder, ac_to_integer(&ctx->ac, val),
-               ac_build_gep0_2(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_pos_cull_x_div_w + chan, 0)));
+               ac_build_gep0(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_pos_cull_x_div_w + chan, 0)));
          }
          break;
 
@@ -1111,7 +1111,7 @@ void gfx10_ngg_culling_build_end(struct si_shader_context *ctx)
    /* Initialize the packed data. */
    LLVMBuildStore(
       builder, packed_data,
-      ac_build_gep0_2(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_packed_data, 0)));
+      ac_build_gep0(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_packed_data, 0)));
    ac_build_endif(&ctx->ac, ctx->merged_wrap_if_label);
 
    ac_build_waitcnt(&ctx->ac, AC_WAIT_LGKM);
@@ -1208,7 +1208,7 @@ void gfx10_ngg_culling_build_end(struct si_shader_context *ctx)
                continue;
 
             LLVMValueRef idx = LLVMConstInt(ctx->ac.i32, index, 0);
-            LLVMValueRef v = ac_build_gep0_2(&ctx->ac, gs_vtxptr[vtx].t, gs_vtxptr[vtx].v, idx);
+            LLVMValueRef v = ac_build_gep0(&ctx->ac, gs_vtxptr[vtx].t, gs_vtxptr[vtx].v, idx);
             pos[vtx][chan] = LLVMBuildLoad2(builder, ac_build_gep0_type(gs_vtxptr[vtx].t, idx), v, "");
             pos[vtx][chan] = ac_to_float(&ctx->ac, pos[vtx][chan]);
          }
@@ -1305,7 +1305,7 @@ void gfx10_ngg_culling_build_end(struct si_shader_context *ctx)
          LLVMBuildStore(
             builder, ac_to_integer(&ctx->ac,
                                    LLVMBuildLoad2(builder, ctx->ac.f32, addrs[4 * pos_index + chan], "")),
-            ac_build_gep0_2(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_pos_x + chan, 0)));
+            ac_build_gep0(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_pos_x + chan, 0)));
       }
 
       /* Store VertexID and InstanceID into LDS. ES threads will have to load them
@@ -1315,24 +1315,24 @@ void gfx10_ngg_culling_build_end(struct si_shader_context *ctx)
       if (ctx->stage == MESA_SHADER_VERTEX) {
          LLVMBuildStore(
             builder, ctx->abi.vertex_id,
-            ac_build_gep0_2(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_vertex_id, 0)));
+            ac_build_gep0(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_vertex_id, 0)));
          if (uses_instance_id) {
             LLVMBuildStore(
                builder, ctx->abi.instance_id,
-               ac_build_gep0_2(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_instance_id, 0)));
+               ac_build_gep0(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_instance_id, 0)));
          }
       } else {
          assert(ctx->stage == MESA_SHADER_TESS_EVAL);
          LLVMBuildStore(builder, ac_to_integer(&ctx->ac, ac_get_arg(&ctx->ac, ctx->args.tes_u)),
-                        ac_build_gep0_2(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_tes_u, 0)));
+                        ac_build_gep0(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_tes_u, 0)));
          LLVMBuildStore(builder, ac_to_integer(&ctx->ac, ac_get_arg(&ctx->ac, ctx->args.tes_v)),
-                        ac_build_gep0_2(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_tes_v, 0)));
+                        ac_build_gep0(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_tes_v, 0)));
          LLVMBuildStore(builder, LLVMBuildTrunc(builder, ac_get_arg(&ctx->ac, ctx->args.tes_rel_patch_id), ctx->ac.i8, ""),
                         si_build_gep_i8(ctx, new_vtx.value, lds_byte2_tes_rel_patch_id));
          if (uses_tes_prim_id) {
             LLVMBuildStore(
                builder, ac_get_arg(&ctx->ac, ctx->args.tes_patch_id),
-               ac_build_gep0_2(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_tes_patch_id, 0)));
+               ac_build_gep0(&ctx->ac, new_vtx.t, new_vtx.v, LLVMConstInt(ctx->ac.i32, lds_tes_patch_id, 0)));
          }
       }
    }
@@ -1411,13 +1411,13 @@ void gfx10_ngg_culling_build_end(struct si_shader_context *ctx)
 
    /* Prepare LDS addresses of the new ES input VGPRs. */
    LLVMValueRef input_vgpr_addresses[4] = {
-      ac_build_gep0_2(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_vertex_id, 0)),
-      ac_build_gep0_2(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_instance_id, 0)),
+      ac_build_gep0(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_vertex_id, 0)),
+      ac_build_gep0(&ctx->ac, es_vtxptr.t, es_vtxptr.v, LLVMConstInt(ctx->ac.i32, lds_instance_id, 0)),
    };
    if (ctx->stage == MESA_SHADER_TESS_EVAL) {
       input_vgpr_addresses[2] = si_build_gep_i8(ctx, es_vtxptr.v, lds_byte2_tes_rel_patch_id);
       if (uses_tes_prim_id) {
-         input_vgpr_addresses[3] = ac_build_gep0_2(&ctx->ac, es_vtxptr.t, es_vtxptr.v,
+         input_vgpr_addresses[3] = ac_build_gep0(&ctx->ac, es_vtxptr.t, es_vtxptr.v,
                                                  LLVMConstInt(ctx->ac.i32, lds_tes_patch_id, 0));
       }
    }
@@ -1545,7 +1545,7 @@ void gfx10_ngg_build_end(struct si_shader_context *ctx)
           */
          if (ctx->so.num_outputs) {
             LLVMValueRef idx = LLVMConstInt(ctx->ac.i32, 4 * i + j, false);
-            tmp = ac_build_gep0_2(&ctx->ac, vertex_ptr.t, vertex_ptr.v, idx);
+            tmp = ac_build_gep0(&ctx->ac, vertex_ptr.t, vertex_ptr.v, idx);
             tmp2 = LLVMBuildLoad2(builder, ac_build_gep0_type(vertex_ptr.t, idx), addrs[4 * i + j], "");
             LLVMTypeRef type = ac_to_integer_type(&ctx->ac, ctx->ac.f32);
             tmp2 = LLVMBuildBitCast(ctx->ac.builder, tmp2, type, "");
@@ -1561,7 +1561,7 @@ void gfx10_ngg_build_end(struct si_shader_context *ctx)
          edgeflag = ac_build_umin(&ctx->ac, edgeflag, ctx->ac.i32_1);
 
          tmp = LLVMConstInt(ctx->ac.i32, ngg_nogs_vertex_size(ctx->shader) - 1, 0);
-         tmp = ac_build_gep0_2(&ctx->ac, vertex_ptr.t, vertex_ptr.v, tmp);
+         tmp = ac_build_gep0(&ctx->ac, vertex_ptr.t, vertex_ptr.v, tmp);
          LLVMBuildStore(builder, edgeflag, tmp);
       }
    }
@@ -1624,7 +1624,7 @@ void gfx10_ngg_build_end(struct si_shader_context *ctx)
          struct ac_llvm_pointer vt = ngg_nogs_vertex_ptr(ctx, vtxindex[i]);
          tmp2 = LLVMConstInt(ctx->ac.i32, ngg_nogs_vertex_size(ctx->shader) - 1, 0);
          tmp = LLVMBuildLoad2(builder, ac_build_gep0_type(vt.t, tmp2),
-                              ac_build_gep0_2(&ctx->ac, vt.t, vt.v, tmp2), "");
+                              ac_build_gep0(&ctx->ac, vt.t, vt.v, tmp2), "");
          tmp = LLVMBuildTrunc(builder, tmp, ctx->ac.i1, "");
 
          user_edgeflags[i] = ac_build_alloca_init(&ctx->ac, tmp, "");
@@ -1655,7 +1655,7 @@ void gfx10_ngg_build_end(struct si_shader_context *ctx)
       struct ac_llvm_pointer vertex_ptr = ngg_nogs_vertex_ptr(ctx, provoking_vtx_index);
 
       LLVMBuildStore(builder, ac_get_arg(&ctx->ac, ctx->args.gs_prim_id),
-                     ac_build_gep0_2(&ctx->ac, vertex_ptr.t, vertex_ptr.v, ctx->ac.i32_0));
+                     ac_build_gep0(&ctx->ac, vertex_ptr.t, vertex_ptr.v, ctx->ac.i32_0));
       ac_build_endif(&ctx->ac, 5400);
    }
 
@@ -1719,7 +1719,7 @@ void gfx10_ngg_build_end(struct si_shader_context *ctx)
 
             for (unsigned j = 0; j < 4; j++) {
                tmp = LLVMConstInt(ctx->ac.i32, lds_pos_x + j, 0);
-               LLVMValueRef v = ac_build_gep0_2(&ctx->ac, vertex_ptr.t, vertex_ptr.v, tmp);
+               LLVMValueRef v = ac_build_gep0(&ctx->ac, vertex_ptr.t, vertex_ptr.v, tmp);
                tmp = LLVMBuildLoad2(builder, ac_build_gep0_type(vertex_ptr.t, tmp), v, "");
                outputs[i].values[j] = LLVMBuildBitCast(ctx->ac.builder, tmp,
                                                        ac_to_float_type(&ctx->ac, ctx->ac.f32), "");
@@ -1742,7 +1742,7 @@ void gfx10_ngg_build_end(struct si_shader_context *ctx)
 
             struct ac_llvm_pointer vt = ngg_nogs_vertex_ptr(ctx, gfx10_get_thread_id_in_tg(ctx));
             outputs[i].values[0] = LLVMBuildLoad2(
-               builder, ac_build_gep0_type(vt.t, ctx->ac.i32_0), ac_build_gep0_2(&ctx->ac, vt.t, vt.v, ctx->ac.i32_0), "");
+               builder, ac_build_gep0_type(vt.t, ctx->ac.i32_0), ac_build_gep0(&ctx->ac, vt.t, vt.v, ctx->ac.i32_0), "");
          } else {
             assert(ctx->stage == MESA_SHADER_TESS_EVAL);
             outputs[i].values[0] = si_get_primitive_id(ctx, 0);
@@ -1821,7 +1821,7 @@ static struct ac_llvm_pointer ngg_gs_vertex_ptr(struct si_shader_context *ctx, L
    }
 
    return (struct ac_llvm_pointer) {
-      .value = ac_build_gep0_2(&ctx->ac, storage.t, storage.v, vertexidx),
+      .value = ac_build_gep0(&ctx->ac, storage.t, storage.v, vertexidx),
       .pointee_type = ac_build_gep0_type(storage.t, vertexidx)
    };
 }
@@ -1948,7 +1948,7 @@ void gfx10_ngg_gs_emit_begin(struct si_shader_context *ctx)
    tmp = LLVMBuildICmp(builder, LLVMIntULT, tid, LLVMConstInt(ctx->ac.i32, 4, false), "");
    ac_build_ifcc(&ctx->ac, tmp, 5090);
    {
-      LLVMValueRef ptr = ac_build_gep0_2(&ctx->ac, scratchptr.t, scratchptr.v, tid);
+      LLVMValueRef ptr = ac_build_gep0(&ctx->ac, scratchptr.t, scratchptr.v, tid);
       LLVMBuildStore(builder, ctx->ac.i32_0, ptr);
    }
    ac_build_endif(&ctx->ac, 5090);
@@ -2033,7 +2033,7 @@ void gfx10_ngg_gs_build_end(struct si_shader_context *ctx)
       {
          LLVMBuildAtomicRMW(
             builder, LLVMAtomicRMWBinOpAdd,
-            ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, LLVMConstInt(ctx->ac.i32, stream, false)),
+            ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, LLVMConstInt(ctx->ac.i32, stream, false)),
             numprims, LLVMAtomicOrderingMonotonic, false);
       }
       ac_build_endif(&ctx->ac, 5105);
@@ -2069,7 +2069,7 @@ void gfx10_ngg_gs_build_end(struct si_shader_context *ctx)
                             "");
          struct ac_llvm_pointer vt = ngg_gs_vertex_ptr(ctx, tmp);
          nggso.vertices[i].t = ac_build_gep0_type(vt.t, ctx->ac.i32_0);
-         nggso.vertices[i].v = ac_build_gep0_2(&ctx->ac, vt.t, vt.v, ctx->ac.i32_0);
+         nggso.vertices[i].v = ac_build_gep0(&ctx->ac, vt.t, vt.v, ctx->ac.i32_0);
       }
 
       build_streamout(ctx, &nggso);
@@ -2097,7 +2097,7 @@ void gfx10_ngg_gs_build_end(struct si_shader_context *ctx)
          }
 
          tmp = LLVMBuildLoad2(builder, ctx->ac.i32,
-                              ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v,
+                              ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v,
                                             tid), "");
          LLVMValueRef args[] = {
             tmp,           ngg_get_query_buf(ctx),
@@ -2136,7 +2136,7 @@ void gfx10_ngg_gs_build_end(struct si_shader_context *ctx)
             tmp = LLVMBuildSub(builder, tid, LLVMConstInt(ctx->ac.i32, verts_per_prim - i - 1, false), "");
             struct ac_llvm_pointer vt = ngg_gs_vertex_ptr(ctx, tmp);
             vtxptr[i].t = ac_build_gep0_type(vt.t, ctx->ac.i32_0);
-            vtxptr[i].v = ac_build_gep0_2(&ctx->ac, vt.t, vt.v, ctx->ac.i32_0);
+            vtxptr[i].v = ac_build_gep0(&ctx->ac, vt.t, vt.v, ctx->ac.i32_0);
          }
 
          for (unsigned i = 0; i < info->num_outputs; i++) {
@@ -2157,7 +2157,7 @@ void gfx10_ngg_gs_build_end(struct si_shader_context *ctx)
                         continue;
 
                      LLVMValueRef idx = LLVMConstInt(ctx->ac.i32, 4 * i + comp, false);
-                     tmp = ac_build_gep0_2(&ctx->ac, vtxptr[vert].t, vtxptr[vert].v, idx);
+                     tmp = ac_build_gep0(&ctx->ac, vtxptr[vert].t, vtxptr[vert].v, idx);
                      pos[vert][comp] = LLVMBuildLoad2(builder,
                                                       ac_build_gep0_type(vtxptr[vert].t, idx),
                                                       tmp, "");
@@ -2229,7 +2229,7 @@ void gfx10_ngg_gs_build_end(struct si_shader_context *ctx)
    vertlive_scan.enable_reduce = true;
    vertlive_scan.enable_exclusive = true;
    vertlive_scan.src = vertlive;
-   vertlive_scan.scratch = ac_build_gep0_2(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, ctx->ac.i32_0);
+   vertlive_scan.scratch = ac_build_gep0(&ctx->ac, ctx->gs_ngg_scratch.t, ctx->gs_ngg_scratch.v, ctx->ac.i32_0);
    vertlive_scan.waveidx = get_wave_id_in_tg(ctx);
    vertlive_scan.numwaves = get_tgsize(ctx);
    vertlive_scan.maxwaves = DIV_ROUND_UP(256, ctx->ac.wave_size);
diff --git a/src/gallium/drivers/radeonsi/si_shader_llvm.c b/src/gallium/drivers/radeonsi/si_shader_llvm.c
index 2b9d8a13ea0..e0d6cfaa713 100644
--- a/src/gallium/drivers/radeonsi/si_shader_llvm.c
+++ b/src/gallium/drivers/radeonsi/si_shader_llvm.c
@@ -767,7 +767,7 @@ static LLVMValueRef si_llvm_load_intrinsic(struct ac_shader_abi *abi, nir_intrin
       LLVMValueRef slot = LLVMConstInt(ctx->ac.i32, SI_HS_CONST_DEFAULT_TESS_LEVELS, 0);
       LLVMValueRef buf = ac_get_arg(&ctx->ac, ctx->internal_bindings);
       LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
-      buf = ac_build_load_to_sgpr2(&ctx->ac, type, buf, slot);
+      buf = ac_build_load_to_sgpr(&ctx->ac, type, buf, slot);
       int offset = op == nir_intrinsic_load_tess_level_inner_default ? 4 : 0;
       LLVMValueRef val[4];
 
@@ -816,7 +816,7 @@ static LLVMValueRef si_llvm_load_intrinsic(struct ac_shader_abi *abi, nir_intrin
 
    case nir_intrinsic_load_clip_half_line_width_amd: {
       LLVMValueRef ptr = ac_get_arg(&ctx->ac, ctx->small_prim_cull_info);
-      return ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.v2f32, ptr, LLVMConstInt(ctx->ac.i32, 4, 0));
+      return ac_build_load_to_sgpr(&ctx->ac, ctx->ac.v2f32, ptr, LLVMConstInt(ctx->ac.i32, 4, 0));
    }
 
    case nir_intrinsic_load_viewport_xy_scale_and_offset: {
@@ -824,7 +824,7 @@ static LLVMValueRef si_llvm_load_intrinsic(struct ac_shader_abi *abi, nir_intrin
       LLVMValueRef ptr = ac_get_arg(&ctx->ac, ctx->small_prim_cull_info);
       LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->small_prim_cull_info);
       LLVMValueRef terms =
-         ac_build_load_to_sgpr2(&ctx->ac, type, ptr, prim_is_lines ? ctx->ac.i32_1 : ctx->ac.i32_0);
+         ac_build_load_to_sgpr(&ctx->ac, type, ptr, prim_is_lines ? ctx->ac.i32_1 : ctx->ac.i32_0);
       return LLVMBuildBitCast(ctx->ac.builder, terms, ctx->ac.v4f32, "");
    }
 
@@ -881,7 +881,7 @@ static LLVMValueRef si_llvm_load_user_clip_plane(struct ac_shader_abi *abi, unsi
    LLVMValueRef ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
    LLVMValueRef constbuf_index = LLVMConstInt(ctx->ac.i32, SI_VS_CONST_CLIP_PLANES, 0);
-   LLVMValueRef const_resource = ac_build_load_to_sgpr2(&ctx->ac, type, ptr, constbuf_index);
+   LLVMValueRef const_resource = ac_build_load_to_sgpr(&ctx->ac, type, ptr, constbuf_index);
    LLVMValueRef addr = LLVMConstInt(ctx->ac.i32, ucp_id * 16, 0);
    return ac_build_buffer_load(&ctx->ac, const_resource, 4, NULL, addr, NULL,
                                ctx->ac.f32, 0, true, true);
@@ -893,7 +893,7 @@ static LLVMValueRef si_llvm_load_streamout_buffer(struct ac_shader_abi *abi, uns
    LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
 
-   return ac_build_load_to_sgpr2(
+   return ac_build_load_to_sgpr(
       &ctx->ac, type, buf_ptr, LLVMConstInt(ctx->ac.i32, SI_VS_STREAMOUT_BUF0 + buffer, false));
 }
 
@@ -933,7 +933,7 @@ bool si_llvm_translate_nir(struct si_shader_context *ctx, struct si_shader *shad
          LLVMValueRef buf = ac_get_arg(&ctx->ac, ctx->internal_bindings);
          LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
          ctx->instance_divisor_constbuf =
-            ac_build_load_to_sgpr2(
+            ac_build_load_to_sgpr(
                &ctx->ac, type, buf, LLVMConstInt(ctx->ac.i32, SI_VS_CONST_INSTANCE_DIVISORS, 0));
       }
       break;
diff --git a/src/gallium/drivers/radeonsi/si_shader_llvm_gs.c b/src/gallium/drivers/radeonsi/si_shader_llvm_gs.c
index dda09dc38ff..60c028761ae 100644
--- a/src/gallium/drivers/radeonsi/si_shader_llvm_gs.c
+++ b/src/gallium/drivers/radeonsi/si_shader_llvm_gs.c
@@ -101,8 +101,8 @@ static LLVMValueRef ngg_get_emulated_counters_buf(struct si_shader_context *ctx)
    LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
 
-   return ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr,
-                                 LLVMConstInt(ctx->ac.i32, SI_GS_QUERY_EMULATED_COUNTERS_BUF, false));
+   return ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr,
+                                LLVMConstInt(ctx->ac.i32, SI_GS_QUERY_EMULATED_COUNTERS_BUF, false));
 }
 
 void si_llvm_gs_build_end(struct si_shader_context *ctx)
@@ -266,7 +266,7 @@ void si_preload_esgs_ring(struct si_shader_context *ctx)
       LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
       LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
 
-      ctx->esgs_ring = ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr, offset);
+      ctx->esgs_ring = ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr, offset);
 
       if (ctx->stage != MESA_SHADER_GEOMETRY) {
          LLVMValueRef desc1 = LLVMBuildExtractElement(builder, ctx->esgs_ring, ctx->ac.i32_1, "");
@@ -309,7 +309,7 @@ void si_preload_gs_rings(struct si_shader_context *ctx)
    LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, SI_RING_GSVS, 0);
    LLVMValueRef buf_ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
-   LLVMValueRef base_ring = ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr, offset);
+   LLVMValueRef base_ring = ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr, offset);
 
    /* The conceptual layout of the GSVS ring is
     *   v0c0 .. vLv0 v0c1 .. vLc1 ..
@@ -438,7 +438,7 @@ struct si_shader *si_generate_gs_copy_shader(struct si_screen *sscreen,
    LLVMValueRef buf_ptr = ac_get_arg(&ctx.ac, ctx.internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx.ac, &ctx.args, ctx.internal_bindings);
    ctx.gsvs_ring[0] =
-      ac_build_load_to_sgpr2(&ctx.ac, type, buf_ptr, LLVMConstInt(ctx.ac.i32, SI_RING_GSVS, 0));
+      ac_build_load_to_sgpr(&ctx.ac, type, buf_ptr, LLVMConstInt(ctx.ac.i32, SI_RING_GSVS, 0));
 
    LLVMValueRef voffset =
       LLVMBuildMul(ctx.ac.builder, ctx.abi.vertex_id, LLVMConstInt(ctx.ac.i32, 4, 0), "");
diff --git a/src/gallium/drivers/radeonsi/si_shader_llvm_ps.c b/src/gallium/drivers/radeonsi/si_shader_llvm_ps.c
index 9277124096a..c7660a3caa0 100644
--- a/src/gallium/drivers/radeonsi/si_shader_llvm_ps.c
+++ b/src/gallium/drivers/radeonsi/si_shader_llvm_ps.c
@@ -37,7 +37,7 @@ static LLVMValueRef load_sample_position(struct ac_shader_abi *abi, LLVMValueRef
    LLVMValueRef desc = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMValueRef buf_index = LLVMConstInt(ctx->ac.i32, SI_PS_CONST_SAMPLE_POSITIONS, 0);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
-   LLVMValueRef resource = ac_build_load_to_sgpr2(&ctx->ac, type, desc, buf_index);
+   LLVMValueRef resource = ac_build_load_to_sgpr(&ctx->ac, type, desc, buf_index);
 
    /* offset = sample_id * 8  (8 = 2 floats containing samplepos.xy) */
    LLVMValueRef offset0 =
@@ -70,7 +70,7 @@ static LLVMValueRef si_nir_emit_fbfetch(struct ac_shader_abi *abi)
    ptr =
       LLVMBuildPointerCast(ctx->ac.builder, ptr, ac_array_in_const32_addr_space(ctx->ac.v8i32), "");
    image =
-      ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.v8i32, ptr, LLVMConstInt(ctx->ac.i32, SI_PS_IMAGE_COLORBUF0 / 2, 0));
+      ac_build_load_to_sgpr(&ctx->ac, ctx->ac.v8i32, ptr, LLVMConstInt(ctx->ac.i32, SI_PS_IMAGE_COLORBUF0 / 2, 0));
 
    unsigned chan = 0;
 
@@ -90,7 +90,7 @@ static LLVMValueRef si_nir_emit_fbfetch(struct ac_shader_abi *abi)
        ctx->shader->key.ps.mono.fbfetch_msaa &&
        !(ctx->screen->debug_flags & DBG(NO_FMASK))) {
 
-      fmask = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.v8i32, ptr,
+      fmask = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.v8i32, ptr,
                                     LLVMConstInt(ctx->ac.i32, SI_PS_IMAGE_COLORBUF0_FMASK / 2, 0));
 
       ac_apply_fmask_to_sample(&ctx->ac, fmask, args.coords,
@@ -550,7 +550,7 @@ static void si_llvm_emit_polygon_stipple(struct si_shader_context *ctx,
    /* Load the buffer descriptor. */
    slot = LLVMConstInt(ctx->ac.i32, SI_PS_CONST_POLY_STIPPLE, 0);
 
-   desc = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.v4i32, param_internal_bindings, slot);
+   desc = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.v4i32, param_internal_bindings, slot);
 
    /* The stipple pattern is 32x32, each row has 32 bits. */
    offset = LLVMBuildMul(builder, address[1], LLVMConstInt(ctx->ac.i32, 4, 0), "");
diff --git a/src/gallium/drivers/radeonsi/si_shader_llvm_resources.c b/src/gallium/drivers/radeonsi/si_shader_llvm_resources.c
index bac1143d482..23ce4f0e5c0 100644
--- a/src/gallium/drivers/radeonsi/si_shader_llvm_resources.c
+++ b/src/gallium/drivers/radeonsi/si_shader_llvm_resources.c
@@ -104,10 +104,10 @@ static LLVMValueRef load_ubo(struct ac_shader_abi *abi, LLVMValueRef index)
    index =
       LLVMBuildAdd(ctx->ac.builder, index, LLVMConstInt(ctx->ac.i32, SI_NUM_SHADER_BUFFERS, 0), "");
 
-   return ac_build_load_to_sgpr2(&ctx->ac,
-                                 ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->const_and_shader_buffers),
-                                 ptr,
-                                 index);
+   return ac_build_load_to_sgpr(&ctx->ac,
+                                ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->const_and_shader_buffers),
+                                ptr,
+                                index);
 }
 
 static LLVMValueRef load_ssbo(struct ac_shader_abi *abi, LLVMValueRef index, bool write, bool non_uniform)
@@ -124,9 +124,9 @@ static LLVMValueRef load_ssbo(struct ac_shader_abi *abi, LLVMValueRef index, boo
    index = LLVMBuildSub(ctx->ac.builder, LLVMConstInt(ctx->ac.i32, SI_NUM_SHADER_BUFFERS - 1, 0),
                         index, "");
 
-   return ac_build_load_to_sgpr2(&ctx->ac,
-                                 ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->const_and_shader_buffers),
-                                 rsrc_ptr, index);
+   return ac_build_load_to_sgpr(&ctx->ac,
+                                ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->const_and_shader_buffers),
+                                rsrc_ptr, index);
 }
 
 /**
@@ -197,9 +197,9 @@ static LLVMValueRef si_load_image_desc(struct si_shader_context *ctx, LLVMTypeRe
    }
 
    if (bindless)
-      rsrc = ac_build_load_to_sgpr_uint_wraparound2(&ctx->ac, type, list, index);
+      rsrc = ac_build_load_to_sgpr_uint_wraparound(&ctx->ac, type, list, index);
    else
-      rsrc = ac_build_load_to_sgpr2(&ctx->ac, type, list, index);
+      rsrc = ac_build_load_to_sgpr(&ctx->ac, type, list, index);
 
    if (desc_type == AC_DESC_IMAGE)
       rsrc = fixup_image_desc(ctx, rsrc, uses_store);
@@ -248,7 +248,7 @@ static LLVMValueRef si_load_sampler_desc(struct si_shader_context *ctx, LLVMType
       unreachable("Plane descriptor requested in radeonsi.");
    }
 
-   return ac_build_load_to_sgpr2(&ctx->ac, list_type, list, index);
+   return ac_build_load_to_sgpr(&ctx->ac, list_type, list, index);
 }
 
 static LLVMValueRef si_nir_load_sampler_desc(struct ac_shader_abi *abi, unsigned descriptor_set,
diff --git a/src/gallium/drivers/radeonsi/si_shader_llvm_vs.c b/src/gallium/drivers/radeonsi/si_shader_llvm_vs.c
index f9ddea92c99..d11ad9ffef6 100644
--- a/src/gallium/drivers/radeonsi/si_shader_llvm_vs.c
+++ b/src/gallium/drivers/radeonsi/si_shader_llvm_vs.c
@@ -169,8 +169,8 @@ static void load_input_vs(struct si_shader_context *ctx, unsigned input_index, L
    } else {
       unsigned index = input_index - num_vbos_in_user_sgprs;
       LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->args.vertex_buffers);
-      vb_desc = ac_build_load_to_sgpr2(&ctx->ac, type, ac_get_arg(&ctx->ac, ctx->args.vertex_buffers),
-                                       LLVMConstInt(ctx->ac.i32, index, 0));
+      vb_desc = ac_build_load_to_sgpr(&ctx->ac, type, ac_get_arg(&ctx->ac, ctx->args.vertex_buffers),
+                                      LLVMConstInt(ctx->ac.i32, index, 0));
    }
 
    if (ctx->abi.vertex_id_replaced) {
@@ -418,7 +418,7 @@ void si_llvm_emit_streamout(struct si_shader_context *ctx, struct si_shader_outp
 
          LLVMValueRef offset = LLVMConstInt(ctx->ac.i32, SI_VS_STREAMOUT_BUF0 + i, 0);
 
-         so_buffers[i] = ac_build_load_to_sgpr2(&ctx->ac, type, buf_ptr, offset);
+         so_buffers[i] = ac_build_load_to_sgpr(&ctx->ac, type, buf_ptr, offset);
 
          LLVMValueRef so_offset = ac_get_arg(&ctx->ac, ctx->args.streamout_offset[i]);
          so_offset = LLVMBuildMul(builder, so_offset, LLVMConstInt(ctx->ac.i32, 4, 0), "");
@@ -454,7 +454,7 @@ void si_llvm_clipvertex_to_clipdist(struct si_shader_context *ctx,
    LLVMValueRef ptr = ac_get_arg(&ctx->ac, ctx->internal_bindings);
    LLVMTypeRef type = ac_get_arg_pointee_type(&ctx->ac, &ctx->args, ctx->internal_bindings);
    LLVMValueRef constbuf_index = LLVMConstInt(ctx->ac.i32, SI_VS_CONST_CLIP_PLANES, 0);
-   LLVMValueRef const_resource = ac_build_load_to_sgpr2(&ctx->ac, type, ptr, constbuf_index);
+   LLVMValueRef const_resource = ac_build_load_to_sgpr(&ctx->ac, type, ptr, constbuf_index);
    unsigned clipdist_mask = ctx->shader->selector->info.clipdist_mask &
                             ~ctx->shader->key.ge.opt.kill_clip_distances;
 
@@ -819,8 +819,8 @@ void si_llvm_build_vs_exports(struct si_shader_context *ctx, LLVMValueRef num_ex
             LLVMBuildPointerCast(ctx->ac.builder,
                                  ac_get_arg(&ctx->ac, ctx->internal_bindings),
                                  LLVMPointerType(ctx->ac.i32, AC_ADDR_SPACE_CONST_32BIT), "");
-         attr_address = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.i32, ptr,
-                                               LLVMConstInt(ctx->ac.i32, SI_GS_ATTRIBUTE_RING * 4, 0));
+         attr_address = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.i32, ptr,
+                                              LLVMConstInt(ctx->ac.i32, SI_GS_ATTRIBUTE_RING * 4, 0));
       } else {
          attr_address = ac_get_arg(&ctx->ac, ctx->gs_attr_address);
       }
@@ -1039,7 +1039,7 @@ void si_llvm_build_vs_prolog(struct si_shader_context *ctx, union si_shader_part
    if (key->vs_prolog.states.instance_divisor_is_fetched) {
       LLVMValueRef list = si_prolog_get_internal_bindings(ctx);
       LLVMValueRef buf_index = LLVMConstInt(ctx->ac.i32, SI_VS_CONST_INSTANCE_DIVISORS, 0);
-      instance_divisor_constbuf = ac_build_load_to_sgpr2(&ctx->ac, ctx->ac.v4i32, list, buf_index);
+      instance_divisor_constbuf = ac_build_load_to_sgpr(&ctx->ac, ctx->ac.v4i32, list, buf_index);
    }
 
    for (i = 0; i < key->vs_prolog.num_inputs; i++) {