metal : correctly set SIMD support flags on iOS (llama/4923)

* Correctly set support_simdgroup_reduction and support_simdgroup_mm on iPhone/iPad

* log a little bit more info on iOS

diff --git a/ggml-metal.m b/ggml-metal.m
index cae52c9830cb22e11961dcc695c4990e864b7b3c..2ca726055f9ea9e421c5043db212bc17f427d650 100644 (file)
--- a/ggml-metal.m
+++ b/ggml-metal.m
@@ -330,7 +330,6 @@ static struct ggml_metal_context * ggml_metal_init(int n_cb) {
         }
     }
 
-#if TARGET_OS_OSX
     // print MTL GPU family:
     GGML_METAL_LOG_INFO("%s: GPU name:   %s\n", __func__, [[ctx->device name] UTF8String]);
 
@@ -370,6 +369,7 @@ static struct ggml_metal_context * ggml_metal_init(int n_cb) {
     GGML_METAL_LOG_INFO("%s: simdgroup reduction support   = %s\n",       __func__, ctx->support_simdgroup_reduction ? "true" : "false");
     GGML_METAL_LOG_INFO("%s: simdgroup matrix mul. support = %s\n",       __func__, ctx->support_simdgroup_mm ? "true" : "false");
     GGML_METAL_LOG_INFO("%s: hasUnifiedMemory              = %s\n",       __func__, ctx->device.hasUnifiedMemory ? "true" : "false");
+#if TARGET_OS_OSX
     GGML_METAL_LOG_INFO("%s: recommendedMaxWorkingSetSize  = %8.2f MB\n", __func__, ctx->device.recommendedMaxWorkingSetSize / 1e6);
     if (ctx->device.maxTransferRate != 0) {
         GGML_METAL_LOG_INFO("%s: maxTransferRate               = %8.2f MB/s\n", __func__, ctx->device.maxTransferRate / 1e6);