ret <16 x i8> %tmp1
}
-define <2 x i64> @pmovsxbd_1(i32* %p) nounwind {
-; X32-LABEL: pmovsxbd_1:
-; X32: ## BB#0: ## %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: pmovsxbd (%eax), %xmm0
-; X32-NEXT: retl
-;
-; X64-LABEL: pmovsxbd_1:
-; X64: ## BB#0: ## %entry
-; X64-NEXT: pmovsxbd (%rdi), %xmm0
-; X64-NEXT: retq
-entry:
- %0 = load i32* %p, align 4
- %1 = insertelement <4 x i32> undef, i32 %0, i32 0
- %2 = insertelement <4 x i32> %1, i32 0, i32 1
- %3 = insertelement <4 x i32> %2, i32 0, i32 2
- %4 = insertelement <4 x i32> %3, i32 0, i32 3
- %5 = bitcast <4 x i32> %4 to <16 x i8>
- %6 = tail call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %5) nounwind readnone
- %7 = bitcast <4 x i32> %6 to <2 x i64>
- ret <2 x i64> %7
-}
-
-define <2 x i64> @pmovsxwd_1(i64* %p) nounwind readonly {
-; X32-LABEL: pmovsxwd_1:
-; X32: ## BB#0: ## %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: pmovsxwd (%eax), %xmm0
-; X32-NEXT: retl
-;
-; X64-LABEL: pmovsxwd_1:
-; X64: ## BB#0: ## %entry
-; X64-NEXT: pmovsxwd (%rdi), %xmm0
-; X64-NEXT: retq
-entry:
- %0 = load i64* %p ; <i64> [#uses=1]
- %tmp2 = insertelement <2 x i64> zeroinitializer, i64 %0, i32 0 ; <<2 x i64>> [#uses=1]
- %1 = bitcast <2 x i64> %tmp2 to <8 x i16> ; <<8 x i16>> [#uses=1]
- %2 = tail call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %1) nounwind readnone ; <<4 x i32>> [#uses=1]
- %3 = bitcast <4 x i32> %2 to <2 x i64> ; <<2 x i64>> [#uses=1]
- ret <2 x i64> %3
-}
-
define <2 x i64> @pmovzxbq_1() nounwind {
; X32-LABEL: pmovzxbq_1:
; X32: ## BB#0: ## %entry
; X64-NEXT: pmovzxbq {{.*#+}} xmm0 = mem[0],zero,zero,zero,zero,zero,zero,zero,mem[1],zero,zero,zero,zero,zero,zero,zero
; X64-NEXT: retq
entry:
- %0 = load i16* @g16, align 2 ; <i16> [#uses=1]
+ %0 = load i16, i16* @g16, align 2 ; <i16> [#uses=1]
%1 = insertelement <8 x i16> undef, i16 %0, i32 0 ; <<8 x i16>> [#uses=1]
%2 = bitcast <8 x i16> %1 to <16 x i8> ; <<16 x i8>> [#uses=1]
%3 = tail call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %2) nounwind readnone ; <<2 x i64>> [#uses=1]
ret <2 x i64> %3
}
-declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
-declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
define i32 @extractps_1(<4 x float> %v) nounwind {
; X32: ## BB#0:
; X32-NEXT: pushl %eax
; X32-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
-; X32-NEXT: addss LCPI7_0, %xmm0
+; X32-NEXT: addss LCPI5_0, %xmm0
; X32-NEXT: movss %xmm0, (%esp)
; X32-NEXT: flds (%esp)
; X32-NEXT: popl %eax
declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
-define <4 x float> @insertps_2(<4 x float> %t1, float %t2) nounwind {
-; X32-LABEL: insertps_2:
+; When optimizing for speed, prefer blendps over insertps even if it means we have to
+; generate a separate movss to load the scalar operand.
+define <4 x float> @blendps_not_insertps_1(<4 x float> %t1, float %t2) nounwind {
+; X32-LABEL: blendps_not_insertps_1:
+; X32: ## BB#0:
+; X32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X32-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
+; X32-NEXT: retl
+;
+; X64-LABEL: blendps_not_insertps_1:
+; X64: ## BB#0:
+; X64-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
+; X64-NEXT: retq
+ %tmp1 = insertelement <4 x float> %t1, float %t2, i32 0
+ ret <4 x float> %tmp1
+}
+
+; When optimizing for size, generate an insertps if there's a load fold opportunity.
+; The difference between i386 and x86-64 ABIs for the float operand means we should
+; generate an insertps for X32 but not for X64!
+define <4 x float> @insertps_or_blendps(<4 x float> %t1, float %t2) minsize nounwind {
+; X32-LABEL: insertps_or_blendps:
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X32-NEXT: retl
;
-; X64-LABEL: insertps_2:
+; X64-LABEL: insertps_or_blendps:
; X64: ## BB#0:
-; X64-NEXT: insertps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
+; X64-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
; X64-NEXT: retq
%tmp1 = insertelement <4 x float> %t1, float %t2, i32 0
ret <4 x float> %tmp1
}
-define <4 x float> @insertps_3(<4 x float> %t1, <4 x float> %t2) nounwind {
-; X32-LABEL: insertps_3:
+
+; An insert into the low 32-bits of a vector from the low 32-bits of another vector
+; is always just a blendps because blendps is never more expensive than insertps.
+define <4 x float> @blendps_not_insertps_2(<4 x float> %t1, <4 x float> %t2) nounwind {
+; X32-LABEL: blendps_not_insertps_2:
; X32: ## BB#0:
-; X32-NEXT: insertps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
+; X32-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
; X32-NEXT: retl
;
-; X64-LABEL: insertps_3:
+; X64-LABEL: blendps_not_insertps_2:
; X64: ## BB#0:
-; X64-NEXT: insertps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
+; X64-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
; X64-NEXT: retq
%tmp2 = extractelement <4 x float> %t2, i32 0
%tmp1 = insertelement <4 x float> %t1, float %tmp2, i32 0
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT: retq
entry:
- %0 = load <4 x float>* %pb, align 16
+ %0 = load <4 x float>, <4 x float>* %pb, align 16
%vecinit6 = shufflevector <4 x float> %a, <4 x float> %0, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
ret <4 x float> %vecinit6
}
; X64-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[6,7]
; X64-NEXT: retq
entry:
- %0 = load <4 x i32>* %pb, align 16
+ %0 = load <4 x i32>, <4 x i32>* %pb, align 16
%vecinit6 = shufflevector <4 x i32> %a, <4 x i32> %0, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
ret <4 x i32> %vecinit6
}
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; X64-NEXT: retq
- %1 = load float* %b, align 4
+ %1 = load float, float* %b, align 4
%2 = insertelement <4 x float> undef, float %1, i32 0
%result = shufflevector <4 x float> %a, <4 x float> %2, <4 x i32> <i32 0, i32 4, i32 2, i32 3>
ret <4 x float> %result
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,1,0,1]
; X64-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; X64-NEXT: retq
- %1 = load i32* %b, align 4
+ %1 = load i32, i32* %b, align 4
%2 = insertelement <4 x i32> undef, i32 %1, i32 0
%result = shufflevector <4 x i32> %a, <4 x i32> %2, <4 x i32> <i32 0, i32 1, i32 4, i32 3>
ret <4 x i32> %result
; X32-LABEL: insertps_from_vector_load:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
+; X32-NEXT: insertps $48, (%{{...}}), {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X32-NEXT: retl
;
; X64-LABEL: insertps_from_vector_load:
; X64: ## BB#0:
-; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
+; X64-NEXT: insertps $48, (%{{...}}), {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT: retq
- %1 = load <4 x float>* %pb, align 16
+ %1 = load <4 x float>, <4 x float>* %pb, align 16
%2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 48)
ret <4 x float> %2
}
; X32-LABEL: insertps_from_vector_load_offset:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[1],xmm0[3]
+; X32-NEXT: insertps $32, 4(%{{...}}), {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X32-NEXT: retl
;
; X64-LABEL: insertps_from_vector_load_offset:
; X64: ## BB#0:
-; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[1],xmm0[3]
+; X64-NEXT: insertps $32, 4(%{{...}}), {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X64-NEXT: retq
- %1 = load <4 x float>* %pb, align 16
+ %1 = load <4 x float>, <4 x float>* %pb, align 16
%2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 96)
ret <4 x float> %2
}
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shll $4, %ecx
-; X32-NEXT: insertps {{.*#+}} xmm0 = mem[3],xmm0[1,2,3]
+; X32-NEXT: insertps $0, 12(%{{...}},%{{...}}), {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X32-NEXT: retl
;
; X64-LABEL: insertps_from_vector_load_offset_2:
; X64: ## BB#0:
; X64-NEXT: shlq $4, %rsi
-; X64-NEXT: insertps {{.*#+}} xmm0 = mem[3],xmm0[1,2,3]
+; X64-NEXT: insertps $0, 12(%{{...}},%{{...}}), {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X64-NEXT: retq
- %1 = getelementptr inbounds <4 x float>* %pb, i64 %index
- %2 = load <4 x float>* %1, align 16
+ %1 = getelementptr inbounds <4 x float>, <4 x float>* %pb, i64 %index
+ %2 = load <4 x float>, <4 x float>* %1, align 16
%3 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %2, i32 192)
ret <4 x float> %3
}
; X64-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0,0,0]
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
; X64-NEXT: retq
- %1 = getelementptr inbounds float* %fb, i64 %index
- %2 = load float* %1, align 4
+ %1 = getelementptr inbounds float, float* %fb, i64 %index
+ %2 = load float, float* %1, align 4
%3 = insertelement <4 x float> undef, float %2, i32 0
%4 = insertelement <4 x float> %3, float %2, i32 1
%5 = insertelement <4 x float> %4, float %2, i32 2
; X64-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0,0,0]
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
; X64-NEXT: retq
- %1 = load <4 x float>* %b, align 4
+ %1 = load <4 x float>, <4 x float>* %b, align 4
%2 = extractelement <4 x float> %1, i32 0
%3 = insertelement <4 x float> undef, float %2, i32 0
%4 = insertelement <4 x float> %3, float %2, i32 1
; X64-NEXT: addps %xmm2, %xmm3
; X64-NEXT: addps %xmm3, %xmm0
; X64-NEXT: retq
- %1 = getelementptr inbounds float* %fb, i64 %index
- %2 = load float* %1, align 4
+ %1 = getelementptr inbounds float, float* %fb, i64 %index
+ %2 = load float, float* %1, align 4
%3 = insertelement <4 x float> undef, float %2, i32 0
%4 = insertelement <4 x float> %3, float %2, i32 1
%5 = insertelement <4 x float> %4, float %2, i32 2
; X64-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
; X64-NEXT: movapd %xmm1, %xmm0
; X64-NEXT: retq
- %1 = load float* %b, align 4
+ %1 = load float, float* %b, align 4
%2 = insertelement <4 x float> undef, float %1, i32 0
%result = shufflevector <4 x float> %a, <4 x float> %2, <4 x i32> <i32 4, i32 undef, i32 0, i32 7>
ret <4 x float> %result
; X32-LABEL: pr20087:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],mem[2]
+; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],mem[0]
; X32-NEXT: retl
;
; X64-LABEL: pr20087:
; X64: ## BB#0:
-; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],mem[2]
+; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],mem[0]
; X64-NEXT: retq
- %load = load <4 x float> *%ptr
+ %load = load <4 x float> , <4 x float> *%ptr
%ret = shufflevector <4 x float> %load, <4 x float> %a, <4 x i32> <i32 4, i32 undef, i32 6, i32 2>
ret <4 x float> %ret
}
; Edge case for insertps where we end up with a shuffle with mask=<0, 7, -1, -1>
-define void @insertps_pr20411(i32* noalias nocapture %RET) #1 {
+define void @insertps_pr20411(<4 x i32> %shuffle109, <4 x i32> %shuffle116, i32* noalias nocapture %RET) #1 {
; X32-LABEL: insertps_pr20411:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: pshufd {{.*#+}} xmm0 = mem[2,3,0,1]
-; X32-NEXT: pshufd {{.*#+}} xmm1 = mem[3,1,2,3]
-; X32-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm0[2,3],xmm1[4,5,6,7]
+; X32-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; X32-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
; X32-NEXT: movdqu %xmm1, (%eax)
; X32-NEXT: retl
;
; X64-LABEL: insertps_pr20411:
; X64: ## BB#0:
-; X64-NEXT: pshufd {{.*#+}} xmm0 = mem[2,3,0,1]
-; X64-NEXT: pshufd {{.*#+}} xmm1 = mem[3,1,2,3]
-; X64-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm0[2,3],xmm1[4,5,6,7]
+; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; X64-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
; X64-NEXT: movdqu %xmm1, (%rdi)
; X64-NEXT: retq
- %gather_load = shufflevector <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, <8 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
- %shuffle109 = shufflevector <4 x i32> <i32 4, i32 5, i32 6, i32 7>, <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> ; 4 5 6 7
- %shuffle116 = shufflevector <8 x i32> %gather_load, <8 x i32> undef, <4 x i32> <i32 3, i32 undef, i32 undef, i32 undef> ; 3 x x x
- %shuffle117 = shufflevector <4 x i32> %shuffle109, <4 x i32> %shuffle116, <4 x i32> <i32 4, i32 3, i32 undef, i32 undef> ; 3 7 x x
+ %shuffle117 = shufflevector <4 x i32> %shuffle109, <4 x i32> %shuffle116, <4 x i32> <i32 0, i32 7, i32 undef, i32 undef>
%ptrcast = bitcast i32* %RET to <4 x i32>*
store <4 x i32> %shuffle117, <4 x i32>* %ptrcast, align 4
ret void