{ X86::PTESTrr, X86::PTESTrm, TB_ALIGN_16 },
{ X86::RCPPSr, X86::RCPPSm, TB_ALIGN_16 },
{ X86::RCPSSr, X86::RCPSSm, 0 },
- { X86::RCPSSr_Int, X86::RCPSSm_Int, TB_NO_REVERSE },
{ X86::ROUNDPDr, X86::ROUNDPDm, TB_ALIGN_16 },
{ X86::ROUNDPSr, X86::ROUNDPSm, TB_ALIGN_16 },
{ X86::ROUNDSDr, X86::ROUNDSDm, 0 },
{ X86::ROUNDSSr, X86::ROUNDSSm, 0 },
{ X86::RSQRTPSr, X86::RSQRTPSm, TB_ALIGN_16 },
{ X86::RSQRTSSr, X86::RSQRTSSm, 0 },
- { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, TB_NO_REVERSE },
{ X86::SQRTPDr, X86::SQRTPDm, TB_ALIGN_16 },
{ X86::SQRTPSr, X86::SQRTPSm, TB_ALIGN_16 },
{ X86::SQRTSDr, X86::SQRTSDm, 0 },
- { X86::SQRTSDr_Int, X86::SQRTSDm_Int, TB_NO_REVERSE },
{ X86::SQRTSSr, X86::SQRTSSm, 0 },
- { X86::SQRTSSr_Int, X86::SQRTSSm_Int, TB_NO_REVERSE },
// FIXME: TEST*rr EAX,EAX ---> CMP [mem], 0
{ X86::UCOMISDrr, X86::UCOMISDrm, 0 },
{ X86::UCOMISDrr_Int, X86::UCOMISDrm_Int, TB_NO_REVERSE },
{ X86::PUNPCKLQDQrr, X86::PUNPCKLQDQrm, TB_ALIGN_16 },
{ X86::PUNPCKLWDrr, X86::PUNPCKLWDrm, TB_ALIGN_16 },
{ X86::PXORrr, X86::PXORrm, TB_ALIGN_16 },
+ { X86::RCPSSr_Int, X86::RCPSSm_Int, TB_NO_REVERSE },
{ X86::ROUNDSDr_Int, X86::ROUNDSDm_Int, TB_NO_REVERSE },
{ X86::ROUNDSSr_Int, X86::ROUNDSSm_Int, TB_NO_REVERSE },
+ { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, TB_NO_REVERSE },
{ X86::SBB16rr, X86::SBB16rm, 0 },
{ X86::SBB32rr, X86::SBB32rm, 0 },
{ X86::SBB64rr, X86::SBB64rm, 0 },
{ X86::SBB8rr, X86::SBB8rm, 0 },
{ X86::SHUFPDrri, X86::SHUFPDrmi, TB_ALIGN_16 },
{ X86::SHUFPSrri, X86::SHUFPSrmi, TB_ALIGN_16 },
+ { X86::SQRTSDr_Int, X86::SQRTSDm_Int, TB_NO_REVERSE },
+ { X86::SQRTSSr_Int, X86::SQRTSSm_Int, TB_NO_REVERSE },
{ X86::SUB16rr, X86::SUB16rm, 0 },
{ X86::SUB32rr, X86::SUB32rm, 0 },
{ X86::SUB64rr, X86::SUB64rm, 0 },
declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>) nounwind readnone
; TODO stack_fold_rcpss
-; TODO stack_fold_rcpss_int
+
+define <4 x float> @stack_fold_rcpss_int(<4 x float> %a0, <4 x float> %a1) optsize {
+ ;CHECK-LABEL: stack_fold_rcpss_int
+ ;CHECK: rcpss {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
+ %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+ %2 = call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %a1)
+ %3 = extractelement <4 x float> %2, i32 0
+ %4 = insertelement <4 x float> %a0, float %3, i32 0
+ ret <4 x float> %4
+}
+declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>)
define <2 x double> @stack_fold_roundpd(<2 x double> %a0) {
;CHECK-LABEL: stack_fold_roundpd
declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>) nounwind readnone
; TODO stack_fold_rsqrtss
-; TODO stack_fold_rsqrtss_int
+
+define <4 x float> @stack_fold_rsqrtss_int(<4 x float> %a0, <4 x float> %a1) optsize {
+ ;CHECK-LABEL: stack_fold_rsqrtss_int
+ ;CHECK: rsqrtss {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
+ %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+ %2 = call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %a1)
+ %3 = extractelement <4 x float> %2, i32 0
+ %4 = insertelement <4 x float> %a0, float %3, i32 0
+ ret <4 x float> %4
+}
+declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>)
define <2 x double> @stack_fold_shufpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK-LABEL: stack_fold_shufpd
}
declare double @llvm.sqrt.f64(double) nounwind readnone
-; TODO stack_fold_sqrtsd_int
+define <2 x double> @stack_fold_sqrtsd_int(<2 x double> %a0, <2 x double> %a1) optsize {
+ ;CHECK-LABEL: stack_fold_sqrtsd_int
+ ;CHECK: sqrtsd {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
+ %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+ %2 = call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %a1)
+ %3 = extractelement <2 x double> %2, i32 0
+ %4 = insertelement <2 x double> %a0, double %3, i32 0
+ ret <2 x double> %4
+}
declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
define float @stack_fold_sqrtss(float %a0) minsize {
}
declare float @llvm.sqrt.f32(float) nounwind readnone
-; TODO stack_fold_sqrtss_int
-declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
+define <4 x float> @stack_fold_sqrtss_int(<4 x float> %a0, <4 x float> %a1) optsize {
+ ;CHECK-LABEL: stack_fold_sqrtss_int
+ ;CHECK: sqrtss {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
+ %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+ %2 = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %a1)
+ %3 = extractelement <4 x float> %2, i32 0
+ %4 = insertelement <4 x float> %a0, float %3, i32 0
+ ret <4 x float> %4
+}
+declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>)
define <2 x double> @stack_fold_subpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK-LABEL: stack_fold_subpd