radeonsi: load the right number of components for VS inputs and TBOs

The supported counts are 1, 2, 4. (3=4)

The following snippet loads float, vec2, vec3, and vec4:

Before:
    buffer_load_format_x v9, v4, s[0:3], 0 idxen          ; E0002000 80000904
    buffer_load_format_xyzw v[0:3], v5, s[8:11], 0 idxen  ; E00C2000 80020005
    s_waitcnt vmcnt(0)                                    ; BF8C0F70
    buffer_load_format_xyzw v[2:5], v6, s[12:15], 0 idxen ; E00C2000 80030206
    s_waitcnt vmcnt(0)                                    ; BF8C0F70
    buffer_load_format_xyzw v[5:8], v7, s[4:7], 0 idxen   ; E00C2000 80010507

After:
    buffer_load_format_x v10, v4, s[0:3], 0 idxen         ; E0002000 80000A04
    buffer_load_format_xy v[8:9], v5, s[8:11], 0 idxen    ; E0042000 80020805
    buffer_load_format_xyzw v[0:3], v6, s[12:15], 0 idxen ; E00C2000 80030006
    s_waitcnt vmcnt(0)                                    ; BF8C0F70
    buffer_load_format_xyzw v[3:6], v7, s[4:7], 0 idxen   ; E00C2000 80010307

Reviewed-by: Samuel Pitoiset <[email protected]>

1 files changed, 35 insertions, 0 deletions

diff --git a/src/amd/common/ac_llvm_build.c b/src/amd/common/ac_llvm_build.c
index 6afe7f97236..a5cb72daed5 100644
--- a/src/amd/common/ac_llvm_build.c
+++ b/src/amd/common/ac_llvm_build.c
@@ -461,6 +461,41 @@ ac_build_gather_values(struct ac_llvm_context *ctx,
 	return ac_build_gather_values_extended(ctx, values, value_count, 1, false, false);
 }
 
+/* Expand a scalar or vector to <4 x type> by filling the remaining channels
+ * with undef. Extract at most num_channels components from the input.
+ */
+LLVMValueRef ac_build_expand_to_vec4(struct ac_llvm_context *ctx,
+				     LLVMValueRef value,
+				     unsigned num_channels)
+{
+	LLVMTypeRef elemtype;
+	LLVMValueRef chan[4];
+
+	if (LLVMGetTypeKind(LLVMTypeOf(value)) == LLVMVectorTypeKind) {
+		unsigned vec_size = LLVMGetVectorSize(LLVMTypeOf(value));
+		num_channels = MIN2(num_channels, vec_size);
+
+		if (num_channels >= 4)
+			return value;
+
+		for (unsigned i = 0; i < num_channels; i++)
+			chan[i] = ac_llvm_extract_elem(ctx, value, i);
+
+		elemtype = LLVMGetElementType(LLVMTypeOf(value));
+	} else {
+		if (num_channels) {
+			assert(num_channels == 1);
+			chan[0] = value;
+		}
+		elemtype = LLVMTypeOf(value);
+	}
+
+	while (num_channels < 4)
+		chan[num_channels++] = LLVMGetUndef(elemtype);
+
+	return ac_build_gather_values(ctx, chan, 4);
+}
+
 LLVMValueRef
 ac_build_fdiv(struct ac_llvm_context *ctx,
 	      LLVMValueRef num,