From 4fdec3091f07cf061adc1edd1df9250b470a161b Mon Sep 17 00:00:00 2001
From: gregory <gregory@gaiaplatform.io>
Date: Fri, 2 Feb 2024 10:18:46 -0800
Subject: [PATCH 1/2] Make 64 bit data use lsc version of gather implementation

---
 sycl/include/sycl/ext/intel/esimd/memory.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sycl/include/sycl/ext/intel/esimd/memory.hpp b/sycl/include/sycl/ext/intel/esimd/memory.hpp
index 5d8f13ce82619..7e7f0b80759c0 100644
--- a/sycl/include/sycl/ext/intel/esimd/memory.hpp
+++ b/sycl/include/sycl/ext/intel/esimd/memory.hpp
@@ -3921,7 +3921,7 @@ slm_gather(simd<uint32_t, N / VS> byte_offsets, simd_mask<N / VS> mask,
   static_assert(Alignment >= sizeof(T),
                 "slm_gather() requires at least element-size alignment");
 
-  if constexpr (VS > 1 || (!detail::isPowerOf2(N, 32) &&
+  if constexpr (VS > 1 || (!(detail::isPowerOf2(N, 32) && sizeof(T) <= 4) &&
                            !detail::isMaskedGatherScatterLLVMAvailable())) {
     simd<T, N> PassThru; // Intentionally undefined
     return detail::slm_gather_impl<T, VS, detail::lsc_data_size::default_size>(

From 21b606b0c985adc43cd2de76e4f610f75ffc40da Mon Sep 17 00:00:00 2001
From: "Fine, Gregory" <gregory.fine@intel.com>
Date: Fri, 2 Feb 2024 17:56:56 -0800
Subject: [PATCH 2/2] Add a test

---
 sycl/test/esimd/memory_properties.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sycl/test/esimd/memory_properties.cpp b/sycl/test/esimd/memory_properties.cpp
index 31dbc3e889f4b..936464cd1ff07 100644
--- a/sycl/test/esimd/memory_properties.cpp
+++ b/sycl/test/esimd/memory_properties.cpp
@@ -1303,4 +1303,9 @@ test_slm_gather_scatter(int byte_offset32) {
                                  props_align4);
   slm = slm_gather<float, 32, 2>(ioffset_n16_view, mask_n16, pass_thru_view,
                                  props_align4);
+
+  // Special case to verify calls to slm_gather with 64 bit data type are
+  // transformed to lsc calls
+  // CHECK-COUNT-1: call <32 x double> @llvm.masked.gather.v32f64.v32p3(<32 x ptr addrspace(3)> {{[^)]+}}, i32 8, <32 x i1> {{[^)]+}}, <32 x double> {{[^)]+}})
+  auto slm_double = slm_gather<double>(ioffset_n32, mask_n32);
 }