[llvm] 7196eb2 - [X86] packss.ll - add SSE4.2 test coverage

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2023-07-21T13:32:03+01:00
New Revision: 7196eb254149ff2612790aa32407eb47ceee6eca

URL: https://github.com/llvm/llvm-project/commit/7196eb254149ff2612790aa32407eb47ceee6eca
DIFF: https://github.com/llvm/llvm-project/commit/7196eb254149ff2612790aa32407eb47ceee6eca.diff

LOG: [X86] packss.ll - add SSE4.2 test coverage

Added: 
    

Modified: 
    llvm/test/CodeGen/X86/packss.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/X86/packss.ll b/llvm/test/CodeGen/X86/packss.ll
index 341bac87d47afa..6a37dd6db294c9 100644
--- a/llvm/test/CodeGen/X86/packss.ll
+++ b/llvm/test/CodeGen/X86/packss.ll
@@ -1,20 +1,32 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=X86-SSE
-; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=AVX --check-prefix=AVX1 --check-prefix=X86-AVX --check-prefix=X86-AVX1
-; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=X86-AVX --check-prefix=X86-AVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=X64-SSE
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=AVX --check-prefix=AVX1 --check-prefix=X64-AVX --check-prefix=X64-AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=X64-AVX --check-prefix=X64-AVX2
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2   | FileCheck %s --check-prefixes=SSE,SSE2,X86-SSE
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X86-SSE
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx    | FileCheck %s --check-prefixes=AVX,AVX1,X86-AVX,X86-AVX1
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2   | FileCheck %s --check-prefixes=AVX,AVX2,X86-AVX,X86-AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2   | FileCheck %s --check-prefixes=SSE,SSE2,X64-SSE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx    | FileCheck %s --check-prefixes=AVX,AVX1,X64-AVX,X64-AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2   | FileCheck %s --check-prefixes=AVX,AVX2,X64-AVX,X64-AVX2
 
 define <4 x i32> @trunc_ashr_v4i64(<4 x i64> %a) nounwind {
-; SSE-LABEL: trunc_ashr_v4i64:
-; SSE:       # %bb.0:
-; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
-; SSE-NEXT:    psrad $31, %xmm1
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
-; SSE-NEXT:    psrad $31, %xmm0
-; SSE-NEXT:    packssdw %xmm1, %xmm0
-; SSE-NEXT:    ret{{[l|q]}}
+; SSE2-LABEL: trunc_ashr_v4i64:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
+; SSE2-NEXT:    psrad $31, %xmm1
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
+; SSE2-NEXT:    psrad $31, %xmm0
+; SSE2-NEXT:    packssdw %xmm1, %xmm0
+; SSE2-NEXT:    ret{{[l|q]}}
+;
+; SSE4-LABEL: trunc_ashr_v4i64:
+; SSE4:       # %bb.0:
+; SSE4-NEXT:    pxor %xmm2, %xmm2
+; SSE4-NEXT:    pxor %xmm3, %xmm3
+; SSE4-NEXT:    pcmpgtq %xmm1, %xmm3
+; SSE4-NEXT:    pcmpgtq %xmm0, %xmm2
+; SSE4-NEXT:    packssdw %xmm3, %xmm2
+; SSE4-NEXT:    movdqa %xmm2, %xmm0
+; SSE4-NEXT:    ret{{[l|q]}}
 ;
 ; AVX1-LABEL: trunc_ashr_v4i64:
 ; AVX1:       # %bb.0:
@@ -40,20 +52,33 @@ define <4 x i32> @trunc_ashr_v4i64(<4 x i64> %a) nounwind {
 }
 
 define <8 x i16> @trunc_ashr_v4i64_bitcast(<4 x i64> %a0) {
-; SSE-LABEL: trunc_ashr_v4i64_bitcast:
-; SSE:       # %bb.0:
-; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[1,3,2,3]
-; SSE-NEXT:    movdqa %xmm1, %xmm2
-; SSE-NEXT:    psrad $31, %xmm2
-; SSE-NEXT:    psrad $17, %xmm1
-; SSE-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
-; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
-; SSE-NEXT:    movdqa %xmm0, %xmm2
-; SSE-NEXT:    psrad $31, %xmm2
-; SSE-NEXT:    psrad $17, %xmm0
-; SSE-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
-; SSE-NEXT:    packssdw %xmm1, %xmm0
-; SSE-NEXT:    ret{{[l|q]}}
+; SSE2-LABEL: trunc_ashr_v4i64_bitcast:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[1,3,2,3]
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    psrad $17, %xmm1
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    psrad $17, %xmm0
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE2-NEXT:    packssdw %xmm1, %xmm0
+; SSE2-NEXT:    ret{{[l|q]}}
+;
+; SSE4-LABEL: trunc_ashr_v4i64_bitcast:
+; SSE4:       # %bb.0:
+; SSE4-NEXT:    pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
+; SSE4-NEXT:    psrad $31, %xmm1
+; SSE4-NEXT:    psrad $17, %xmm2
+; SSE4-NEXT:    pblendw {{.*#+}} xmm2 = xmm2[0,1],xmm1[2,3],xmm2[4,5],xmm1[6,7]
+; SSE4-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE4-NEXT:    psrad $31, %xmm0
+; SSE4-NEXT:    psrad $17, %xmm1
+; SSE4-NEXT:    pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
+; SSE4-NEXT:    packssdw %xmm2, %xmm0
+; SSE4-NEXT:    ret{{[l|q]}}
 ;
 ; AVX1-LABEL: trunc_ashr_v4i64_bitcast:
 ; AVX1:       # %bb.0: