Peephole optimization of ptest-conditioned branch in X86 arch. Performs instruction combining of sequences generated by ptestz/ptestc intrinsics to ptest+jcc pair for SSE and AVX.

Testing: passed 'make check' including LIT tests for all sequences being handled (both SSE and AVX)

Reviewers: Evan Cheng, David Blaikie, Bruno Lopes, Elena Demikhovsky, Chad Rosier, Anton Korobeynikov



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147601 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 489 insertions, 1 deletions

diff --git a/test/CodeGen/X86/avx-brcond.ll b/test/CodeGen/X86/avx-brcond.ll
new file mode 100755
index 0000000..cecacc2
--- /dev/null
+++ b/test/CodeGen/X86/avx-brcond.ll
@@ -0,0 +1,244 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=corei7-avx -mattr=+avx | FileCheck %s
+
+declare i32 @llvm.x86.avx.ptestz.256(<4 x i64> %p1, <4 x i64> %p2) nounwind
+declare i32 @llvm.x86.avx.ptestc.256(<4 x i64> %p1, <4 x i64> %p2) nounwind
+
+define <4 x float> @test1(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test1:
+; CHECK: vptest
+; CHECK-NEXT:	jne
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp ne i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test2(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test2:
+; CHECK: vptest
+; CHECK-NEXT:	je
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp eq i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test3(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test3:
+; CHECK: vptest
+; CHECK-NEXT:	jne
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = trunc i32 %res to i1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test4(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test4:
+; CHECK: vptest
+; CHECK-NEXT:	jae
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp ne i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test5(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test5:
+; CHECK: vptest
+; CHECK-NEXT:	jb
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp eq i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test6(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test6:
+; CHECK: vptest
+; CHECK-NEXT:	jae
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = trunc i32 %res to i1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test7(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test7:
+; CHECK: vptest
+; CHECK-NEXT:	jne
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp eq i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test8(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test8:
+; CHECK: vptest
+; CHECK-NEXT:	je
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp ne i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test9(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test9:
+; CHECK: vptest
+; CHECK-NEXT:	jae
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp eq i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test10(<4 x i64> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test10:
+; CHECK: vptest
+; CHECK-NEXT:	jb
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind 
+  %one = icmp ne i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
diff --git a/test/CodeGen/X86/brcond.ll b/test/CodeGen/X86/brcond.ll
index 5cdc100..ff3b2e4 100644
--- a/test/CodeGen/X86/brcond.ll
+++ b/test/CodeGen/X86/brcond.ll
@@ -1,4 +1,5 @@
-; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=core2 | FileCheck %s
+; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=penryn | FileCheck %s
+
 ; rdar://7475489
 
 define i32 @test1(i32 %a, i32 %b) nounwind ssp {
@@ -106,3 +107,246 @@ bb2:                                              ; preds = %entry, %bb1
   %.0 = fptrunc double %.0.in to float            ; <float> [#uses=1]
   ret float %.0
 }
+
+declare i32 @llvm.x86.sse41.ptestz(<4 x float> %p1, <4 x float> %p2) nounwind
+declare i32 @llvm.x86.sse41.ptestc(<4 x float> %p1, <4 x float> %p2) nounwind
+
+define <4 x float> @test5(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test5:
+; CHECK: ptest
+; CHECK-NEXT:	jne
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp ne i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test6(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test6:
+; CHECK: ptest
+; CHECK-NEXT:	je
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp eq i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test7(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test7:
+; CHECK: ptest
+; CHECK-NEXT:	jne
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = trunc i32 %res to i1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test8(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test8:
+; CHECK: ptest
+; CHECK-NEXT:	jae
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp ne i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test9(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test9:
+; CHECK: ptest
+; CHECK-NEXT:	jb
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp eq i32 %res, 0 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test10(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test10:
+; CHECK: ptest
+; CHECK-NEXT:	jae
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = trunc i32 %res to i1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test11(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test11:
+; CHECK: ptest
+; CHECK-NEXT:	jne
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp eq i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test12(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test12:
+; CHECK: ptest
+; CHECK-NEXT:	je
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp ne i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test13(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test13:
+; CHECK: ptest
+; CHECK-NEXT:	jae
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp eq i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}
+
+define <4 x float> @test14(<4 x float> %a, <4 x float> %b) nounwind {
+entry:
+; CHECK: test14:
+; CHECK: ptest
+; CHECK-NEXT:	jb
+; CHECK: ret
+
+  %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind 
+  %one = icmp ne i32 %res, 1 
+  br i1 %one, label %bb1, label %bb2
+
+bb1:
+  %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+  br label %return
+
+bb2:
+	%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
+	br label %return
+
+return:
+  %e = phi <4 x float> [%c, %bb1], [%d, %bb2]
+  ret <4 x float> %e
+}