AVX-512: minor change in rndscale intrinsic

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207937 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86InstrAVX512.td b/lib/Target/X86/X86InstrAVX512.td
index 72f5aff569badc36df68130222dd8e9042ebe072..1cd1adcfc5b61c5506e543dde691ac05b0f3aab2 100644 (file)
--- a/lib/Target/X86/X86InstrAVX512.td
+++ b/lib/Target/X86/X86InstrAVX512.td
@@ -1384,6 +1384,15 @@ def: Pat<(v8i64 (int_x86_avx512_mask_loadu_q_512 addr:$ptr,
                  (bc_v8i64 (v16i32 immAllZerosV)), GR8:$mask)),
        (VMOVDQU64rmkz (v8i1 (COPY_TO_REGCLASS GR8:$mask, VK8WM)), addr:$ptr)>;
 
+def: Pat<(int_x86_avx512_mask_storeu_d_512 addr:$ptr, (v16i32 VR512:$src),
+          GR16:$mask),
+         (VMOVDQU32mrk addr:$ptr, (v16i1 (COPY_TO_REGCLASS GR16:$mask, VK16WM)),
+            VR512:$src)>;
+def: Pat<(int_x86_avx512_mask_storeu_q_512 addr:$ptr, (v8i64 VR512:$src),
+          GR8:$mask),
+         (VMOVDQU64mrk addr:$ptr, (v8i1 (COPY_TO_REGCLASS GR8:$mask, VK8WM)),
+            VR512:$src)>;
+
 let AddedComplexity = 20 in {
 def : Pat<(v8i64 (vselect VK8WM:$mask, (v8i64 VR512:$src),
                            (bc_v8i64 (v16i32 immAllZerosV)))),
@@ -3754,7 +3763,7 @@ defm VRNDSCALEPSZ : avx512_rndscale<0x08, "vrndscaleps", f512mem, VR512,
                                 EVEX_CD8<32, CD8VF>;
 
 def : Pat<(v16f32 (int_x86_avx512_mask_rndscale_ps_512 (v16f32 VR512:$src1),
-                   imm:$src2, (bc_v16f32 (v16i32 immAllZerosV)), (i16 -1),
+                   imm:$src2, (v16f32 VR512:$src1), (i16 -1),
                    FROUND_CURRENT)),
                    (VRNDSCALEPSZr VR512:$src1, imm:$src2)>;
 
@@ -3764,7 +3773,7 @@ defm VRNDSCALEPDZ : avx512_rndscale<0x09, "vrndscalepd", f512mem, VR512,
                                 VEX_W, EVEX_CD8<64, CD8VF>;
 
 def : Pat<(v8f64 (int_x86_avx512_mask_rndscale_pd_512 (v8f64 VR512:$src1),
-                  imm:$src2, (bc_v8f64 (v16i32 immAllZerosV)), (i8 -1),
+                  imm:$src2, (v8f64 VR512:$src1), (i8 -1),
                   FROUND_CURRENT)),
                    (VRNDSCALEPDZr VR512:$src1, imm:$src2)>;
 

diff --git a/test/CodeGen/X86/avx512-intrinsics.ll b/test/CodeGen/X86/avx512-intrinsics.ll
index 2c57944861c958c9cc5a18d44c3fa84ddc5450ff..e19841a6f9a8e8555adc298fd394598f3b43e1d9 100644 (file)
--- a/test/CodeGen/X86/avx512-intrinsics.ll
+++ b/test/CodeGen/X86/avx512-intrinsics.ll
@@ -78,7 +78,7 @@ declare <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double>, i32, <8
 
 define <8 x double> @test7(<8 x double> %a) {
 ; CHECK: vrndscalepd {{.*}}encoding: [0x62,0xf3,0xfd,0x48,0x09,0xc0,0x0b]
-  %res = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> %a, i32 11, <8 x double> zeroinitializer, i8 -1, i32 4)
+  %res = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> %a, i32 11, <8 x double> %a, i8 -1, i32 4)
   ret <8 x double>%res
 }
 
@@ -86,7 +86,7 @@ declare <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float>, i32, <1
 
 define <16 x float> @test8(<16 x float> %a) {
 ; CHECK: vrndscaleps {{.*}}encoding: [0x62,0xf3,0x7d,0x48,0x08,0xc0,0x0b]
-  %res = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> %a, i32 11, <16 x float> zeroinitializer, i16 -1, i32 4)
+  %res = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> %a, i32 11, <16 x float> %a, i16 -1, i32 4)
   ret <16 x float>%res
 }