ac,radv: do not emit vec3 for raw load/store on SI

It's unsupported, only load/store format with vec3 are supported.

Fixes: 6970a9a6ca ("ac,radv: remove the vec3 restriction with LLVM 9+")"
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

src/amd/common/ac_llvm_build.c

@@ -1167,7 +1167,7 @@ ac_build_llvm8_buffer_store_common(struct ac_llvm_context *ctx,
 	args[idx++] = voffset ? voffset : ctx->i32_0;
 	args[idx++] = soffset ? soffset : ctx->i32_0;
 	args[idx++] = LLVMConstInt(ctx->i32, (glc ? 1 : 0) + (slc ? 2 : 0), 0);
-	unsigned func = HAVE_LLVM < 0x900 && num_channels == 3 ? 4 : num_channels;
+	unsigned func = !ac_has_vec3_support(ctx->chip_class, use_format) && num_channels == 3 ? 4 : num_channels;
 	const char *indexing_kind = structurized ? "struct" : "raw";
 	char name[256], type_name[8];
 
@@ -1227,7 +1227,7 @@ ac_build_buffer_store_dword(struct ac_llvm_context *ctx,
 {
 	/* Split 3 channel stores, because only LLVM 9+ support 3-channel
 	 * intrinsics. */
-	if (num_channels == 3 && HAVE_LLVM < 0x900) {
+	if (num_channels == 3 && !ac_has_vec3_support(ctx->chip_class, false)) {
 		LLVMValueRef v[3], v01;
 
 		for (int i = 0; i < 3; i++) {
@@ -1354,7 +1354,7 @@ ac_build_llvm8_buffer_load_common(struct ac_llvm_context *ctx,
 	args[idx++] = voffset ? voffset : ctx->i32_0;
 	args[idx++] = soffset ? soffset : ctx->i32_0;
 	args[idx++] = LLVMConstInt(ctx->i32, (glc ? 1 : 0) + (slc ? 2 : 0), 0);
-	unsigned func = HAVE_LLVM < 0x900 && num_channels == 3 ? 4 : num_channels;
+	unsigned func = !ac_has_vec3_support(ctx->chip_class, use_format) && num_channels == 3 ? 4 : num_channels;
 	const char *indexing_kind = structurized ? "struct" : "raw";
 	char name[256], type_name[8];
 
@@ -1420,7 +1420,7 @@ ac_build_buffer_load(struct ac_llvm_context *ctx,
 		if (num_channels == 1)
 			return result[0];
 
-		if (num_channels == 3 && HAVE_LLVM < 0x900)
+		if (num_channels == 3 && !ac_has_vec3_support(ctx->chip_class, false))
 			result[num_channels++] = LLVMGetUndef(ctx->f32);
 		return ac_build_gather_values(ctx, result, num_channels);
 	}
@@ -1512,7 +1512,7 @@ ac_build_llvm8_tbuffer_load(struct ac_llvm_context *ctx,
 	args[idx++] = soffset ? soffset : ctx->i32_0;
 	args[idx++] = LLVMConstInt(ctx->i32, dfmt | (nfmt << 4), 0);
 	args[idx++] = LLVMConstInt(ctx->i32, (glc ? 1 : 0) + (slc ? 2 : 0), 0);
-	unsigned func = HAVE_LLVM < 0x900 && num_channels == 3 ? 4 : num_channels;
+	unsigned func = !ac_has_vec3_support(ctx->chip_class, true) && num_channels == 3 ? 4 : num_channels;
 	const char *indexing_kind = structurized ? "struct" : "raw";
 	char name[256], type_name[8];
 
@@ -2011,7 +2011,7 @@ ac_build_llvm8_tbuffer_store(struct ac_llvm_context *ctx,
 	args[idx++] = soffset ? soffset : ctx->i32_0;
 	args[idx++] = LLVMConstInt(ctx->i32, dfmt | (nfmt << 4), 0);
 	args[idx++] = LLVMConstInt(ctx->i32, (glc ? 1 : 0) + (slc ? 2 : 0), 0);
-	unsigned func = HAVE_LLVM < 0x900 && num_channels == 3 ? 4 : num_channels;
+	unsigned func = !ac_has_vec3_support(ctx->chip_class, true) && num_channels == 3 ? 4 : num_channels;
 	const char *indexing_kind = structurized ? "struct" : "raw";
 	char name[256], type_name[8];
 

src/amd/common/ac_llvm_util.h

@@ -147,6 +147,17 @@ bool ac_compile_module_to_binary(struct ac_compiler_passes *p, LLVMModuleRef mod
 void ac_llvm_add_barrier_noop_pass(LLVMPassManagerRef passmgr);
 void ac_enable_global_isel(LLVMTargetMachineRef tm);
 
+static inline bool
+ac_has_vec3_support(enum chip_class chip, bool use_format)
+{
+	if (chip == GFX6 && !use_format) {
+		/* GFX6 only supports vec3 with load/store format. */
+		return false;
+	}
+
+	return HAVE_LLVM >= 0x900;
+}
+
 #ifdef __cplusplus
 }
 #endif

src/amd/common/ac_nir_to_llvm.c

@@ -1576,7 +1576,8 @@ static void visit_store_ssbo(struct ac_nir_context *ctx,
 
 		/* Due to an LLVM limitation with LLVM < 9, split 3-element
 		 * writes into a 2-element and a 1-element write. */
-		if (count == 3 && (elem_size_bytes != 4 || HAVE_LLVM < 0x900)) {
+		if (count == 3 &&
+		    (elem_size_bytes != 4 || !ac_has_vec3_support(ctx->ac.chip_class, false))) {
 			writemask |= 1 << (start + 2);
 			count = 2;
 		}

src/amd/vulkan/radv_nir_to_llvm.c

@@ -2764,7 +2764,7 @@ radv_emit_stream_output(struct radv_shader_context *ctx,
 		/* fall through */
 	case 4: /* as v4i32 */
 		vdata = ac_build_gather_values(&ctx->ac, out,
-					       HAVE_LLVM < 0x900 ?
+					       !ac_has_vec3_support(ctx->ac.chip_class, false) ?
 					       util_next_power_of_two(num_comps) :
 					       num_comps);
 		break;